See axolotl config

axolotl version: 0.12.0.dev0

base_model: NousResearch/Meta-Llama-3-8B
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: true
load_in_4bit: false

datasets:
  - path: cfierro/gsm8k_instr
    type: alpaca
  - path: cfierro/alpaca-en2fr
    type: alpaca
dataset_prepared_path: /workspace/axolotl-datasets/llama3-all
val_set_size: 0.05
output_dir: /workspace/axolotl-outputs/llama3-all-lorar2

sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 2
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
  - embed_tokens
  - lm_head
merge_lora: true

wandb_project: weight-diff-ft
wandb_entity: cfierro
wandb_watch: all
wandb_name: llama3-all-lorar2
wandb_log_model: "false"
hub_model_id: coastalcph/llama3-all-lorar2

gradient_accumulation_steps: 4
micro_batch_size: 2
max_steps: 1000  # 8k examples at most 
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 10
early_stopping_patience: 2
eval_steps: 60  # bs=4*2 -> eval every 8*60=480 examples  
save_steps: 60  # needed for config validation
save_total_limit: 1
load_best_model_at_end: true
weight_decay: 0.0
special_tokens:
   pad_token: <|end_of_text|>

llama3-all-lorar2

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B on the cfierro/gsm8k_instr and the cfierro/alpaca-en2fr datasets. It achieves the following results on the evaluation set:

• Loss: 0.9412

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: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 10
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	1.4447
1.0346	0.2691	60	0.9846
0.99	0.5381	120	0.9511
0.9128	0.8072	180	0.9331
0.7667	1.0762	240	0.9394
0.7454	1.3453	300	0.9412

Framework versions

• PEFT 0.15.2
• Transformers 4.53.1
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2