llama-qwc

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.8.0.dev0

base_model: NousResearch/Llama-3.2-1B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

datasets:
  - path: chrisdboyce/qwc
    type: alpaca

val_set_size: 0.1
output_dir: ./outputs/lora-out

adapter: lora
lora_model_dir:

sequence_len: 2048
sample_packing: true
eval_sample_packing: false


lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1

optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
label_names:
  - labels
tf32: false
evaluation_strategy: "no"

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_ratio: 0.1
evals_per_epoch: 0
# evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
  pad_token: "<|end_of_text|>"

# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

</details><br>

outputs/lora-out

This model is a fine-tuned version of NousResearch/Llama-3.2-1B on the chrisdboyce/qwc 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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• 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
• num_epochs: 1.0

Training results

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0