See axolotl config

axolotl version: 0.9.0

base_model: meta-llama/Llama-3.1-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
gradient_accumulation_steps: 2
micro_batch_size: 8
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001
load_in_8bit: true
load_in_4bit: false
adapter: lora
lora_model_dir: null
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
- k_proj
datasets:
- path: /workspace/FinLoRA/data/train/ner_train.jsonl
  type:
    system_prompt: ''
    field_system: system
    field_instruction: context
    field_output: target
    format: '[INST] {instruction} [/INST]'
    no_input_format: '[INST] {instruction} [/INST]'
dataset_prepared_path: null
val_set_size: 0.02
output_dir: /workspace/FinLoRA/lora/axolotl-output/ner_llama_3_1_8b_8bits_r8_dora
peft_use_dora: true
sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false
wandb_project: finlora_models
wandb_entity: null
wandb_watch: gradients
wandb_name: ner_llama_3_1_8b_8bits_r8_dora
wandb_log_model: 'false'
bf16: auto
tf32: false
gradient_checkpointing: true
resume_from_checkpoint: null
logging_steps: 500
flash_attention: false
deepspeed: deepspeed_configs/zero1.json
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
  pad_token: <|end_of_text|>
chat_template: llama3

workspace/FinLoRA/lora/axolotl-output/ner_llama_3_1_8B_8bits_r8_dora

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the /workspace/FinLoRA/data/train/ner_train.jsonl dataset. It achieves the following results on the evaluation set:

• Loss: 0.0273

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• 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
• num_epochs: 4.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0048	1	8.4867
No log	0.2506	52	0.0123
No log	0.5012	104	0.0191
No log	0.7518	156	0.1266
No log	1.0	208	0.0566
No log	1.2506	260	0.0980
No log	1.5012	312	0.0368
No log	1.7518	364	0.0498
No log	2.0	416	0.0359
No log	2.2506	468	0.0299
0.1814	2.5012	520	0.0228
0.1814	2.7518	572	0.0475
0.1814	3.0	624	0.0495
0.1814	3.2506	676	0.0295
0.1814	3.5012	728	0.0140
0.1814	3.7518	780	0.0273

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.8.0.dev20250319+cu128
• Datasets 3.5.0
• Tokenizers 0.21.1