MN-2407-DSK-QwQify-v0.1-12B

4

9

12.0B

dataset:PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled

by

BeaverAI

Language Model

OTHER

12B params

New

4 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

27GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

12GB+ RAM

Code Examples

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Hugging Face saving configyaml

mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA

# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save

# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false

# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast

# Mixed precision training config
bf16: true
fp16: false
tf32: false

# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false

# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:

# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: train
    type: customchatml-regex-last-only
test_datasets:
  - path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
  - path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
    split: test
    type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:

# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16  # x4 GPUs = 64
eval_batch_size: 16   # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1

# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json

# Garbage Collection
gc_steps: 1

# Debug config
debug: true
seed: 42

# Token config
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  pad_token: "<pad>"
tokens:

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.