README.md

metadata

library_name: transformers
base_model: Emm9625/Llama-3.2-1B-chatml
tags:
  - axolotl
  - generated_from_trainer
datasets:
  - mlabonne/FineTome-100k
model-index:
  - name: Finetome-1b_25-01-19
    results: []

See axolotl config

axolotl version: 0.6.0

# Original base model config
# base_model: Dans-DiscountModels/Meta-Llama-3.2-3B-ChatML
# Using smaller model instead
base_model: Emm9625/Llama-3.2-1B-chatml

# Original tokenizer config
# tokenizer_config: Dans-DiscountModels/Meta-Llama-3.2-3B-ChatML
# Using matching tokenizer for smaller model
tokenizer_config: Emm9625/Llama-3.2-1B-chatml

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

# Chat template configuration
chat_template: chatml

# Dataset configuration
datasets:
  - path: mlabonne/FineTome-100k
    split: train
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
    # shards: 2
    # shard_idx: 0
    
# test_datasets:
#   - path: Emm9625/textwork-00-dedupe-0.75
#     name: smol-constraints
#     split: test
#     type: chat_template
#     field_messages: messages
#     message_field_role: role
#     message_field_content: content
#     train_on_eos: turn
#     shards: 5
#     shard_idx: 0
    
#   - path: Emm9625/textwork-00-dedupe-0.75
#     name: smol-rewrite
#     split: test
#     type: chat_template
#     field_messages: messages
#     message_field_role: role
#     message_field_content: content
  #   train_on_eos: turn
  #   shards: 5
  #   shard_idx: 0

  # - path: Emm9625/textwork-00-dedupe-0.75
  #   name: smol-summarize
  #   split: test
  #   type: chat_template
  #   field_messages: messages
  #   message_field_role: role
  #   message_field_content: content
  #   train_on_eos: turn
  #   shards: 5
  #   shard_idx: 0



dataset_prepared_path: /notebooks/last_run_prepared
val_set_size: 0.00
output_dir: /tmp/meow/
hub_model_id: Emm9625/Finetome-1b_25-01-19
hub_strategy: checkpoint
# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
# Required to be true when used in combination with `push_dataset_to_hub`
hf_use_auth_token: true

# Model configuration
sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:

lora_r: 128
lora_alpha: 256
lora_dropout: 
# 0.05
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj


# Unsloth optimizations
unsloth_cross_entropy_loss: true
unsloth_rms_norm: true
unsloth_rope: true
# Lora Optimizations
# unsloth_lora_mlp: true
# unsloth_lora_qkv: true
# unsloth_lora_o: true


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

# Training configuration
gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 1
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
torch_compile: true

train_on_inputs: false
group_by_length: false
bf16: true
gradient_checkpointing: true
flash_attention: true

# Training monitoring
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_ratio: 0.10
weight_decay: 0.00
saves_per_epoch: 1
evals_per_epoch: 0
save_safetensors: true
wandb_project: Finetome-1b_25-01-19
logging_steps: 1

# Special tokens configuration
special_tokens:
  eos_token: "<|im_end|>"
  bos_token: "<|im_start|>"

fsdp:
fsdp_config:

Finetome-1b_25-01-19

This model is a fine-tuned version of Emm9625/Llama-3.2-1B-chatml on the mlabonne/FineTome-100k dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 158
• num_epochs: 1

Training results

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0