See axolotl config

axolotl version: 0.9.1.post1

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
learning_rate: 0.0001
optimizer: adamw_torch_fused
lr_scheduler: cosine
load_in_8bit: false
load_in_4bit: false
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
datasets:
- path: /workspace/FinLoRA/data/train/ner_train.jsonl
  type:
    field_instruction: context
    field_output: target
    format: '[INST] {instruction} [/INST]'
    no_input_format: '[INST] {instruction} [/INST]'
val_set_size: 0.02
output_dir: /workspace/FinLoRA/lora/axolotl-output/ner_llama_3_1_8b_fp16_r8
sequence_len: 4096
gradient_checkpointing: true
logging_steps: 500
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
  pad_token: <|end_of_text|>
deepspeed: deepspeed_configs/zero1.json
bf16: auto
tf32: false
chat_template: llama3
wandb_name: ner_llama_3_1_8b_fp16_r8

workspace/FinLoRA/lora/axolotl-output/ner_llama_3_1_8b_fp16_r8

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: 0.0404

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: 3
• gradient_accumulation_steps: 2
• total_train_batch_size: 48
• total_eval_batch_size: 24
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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	0.0036	1	8.3561
No log	0.2527	70	0.0025
No log	0.5054	140	0.0317
No log	0.7581	210	0.0201
No log	1.0108	280	0.0501
No log	1.2635	350	0.0577
No log	1.5162	420	0.0542
No log	1.7690	490	0.0492
0.1766	2.0217	560	0.0466
0.1766	2.2744	630	0.0419
0.1766	2.5271	700	0.0450
0.1766	2.7798	770	0.0442
0.1766	3.0325	840	0.0479
0.1766	3.2852	910	0.0456
0.1766	3.5379	980	0.0400
0.0	3.7906	1050	0.0404

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.8.0.dev20250319+cu128
• Datasets 3.5.1
• Tokenizers 0.21.1