intern-rp-lora

4
2.0B
BF16
license:apache-2.0
by
ToastyPigeon
Code Model
OTHER
2B params
New
4 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
5GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2GB+ RAM

Code Examples

git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69
git clone https://github.com/axolotl-ai-cloud/axolotlyaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout bd2a594b8954103719f8d1ef739e2c3267ca36f6
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess intern-rp-test-human.yml
# accelerate launch -m axolotl.cli.train intern-rp-test-human.yml
# python -m axolotl.cli.merge_lora qwen-rp-test-human.yml
# huggingface-cli upload ToastyPigeon/tqi-some-rp-40 train-workspace/merged . --exclude "*.md"
# sleep 10h; runpodctl stop pod $RUNPOD_POD_ID &

# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key

# Model
base_model: internlm/internlm3-8b-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:

# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/intern-rp-lora
hub_strategy: "all_checkpoints"
auto_resume_from_checkpoint: true
#resume_from_checkpoint: ./train-workspace/checkpoint-304
saves_per_epoch: 2
save_total_limit: 4

# Data
sequence_len: 8192 # fits
min_sample_len: 128
chat_template: chatml
dataset_prepared_path: last_run_prepared
datasets:
  - path: ToastyPigeon/some-rp
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    #train_on_inputs: true
  - path: BeaverAI/cedo-unalignment
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: BeaverAI/foundRP
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:1000]
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: ToastyPigeon/SpringDragon-Instruct
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    split: train[:500]
  - path: allenai/tulu-3-sft-personas-instruction-following
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    split: train[:500]
  - path: allura-org/fujin-cleaned-stage-2
    type: completion
    field: text
    split: train[:500]
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true

# Batching
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1

# Evaluation
val_set_size: 100
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false

save_safetensors: true

# WandB
wandb_project: Intern-Rp-Test
#wandb_entity:

gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
  use_reentrant: false

unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# LoRA
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
#peft_use_rslora: true
#loraplus_lr_ratio: 8

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 3e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
#debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:

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

gc_steps: 10
seed: 69

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.