Magnum-v4-SE-70B-LoRA

55
4
1 language
BF16
llama
by
Doctor-Shotgun
Language Model
OTHER
70B params
New
55 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
157GB+ RAM
Mobile
Laptop
Server
Quick Summary

The Magnum v4 series is complete, but here's something a little extra I wanted to tack on as I wasn't entirely satisfied with the results of v4 72B.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
66GB+ RAM

Code Examples

optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v4-se-70b-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.3
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/nopm_claude_writing_fixed
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
dataset_prepared_path: /home/docshotgun/data/magnum-70b-data
val_set_size: 0.0
output_dir: /home/docshotgun/data/70b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4.0e-5
max_grad_norm: 3.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|finetune_right_pad_id|>

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.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.