See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: numind/NuExtract-v1.5
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e68846169b35e5f6_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e68846169b35e5f6_train_data.json
  type:
    field_instruction: sentence1
    field_output: sentence2
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: lesso07/4f0bc850-8791-4641-9ae4-1a1482df5a4d
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000207
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 2000
micro_batch_size: 4
mlflow_experiment_name: /tmp/e68846169b35e5f6_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 500
saves_per_epoch: null
seed: 70
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: a0005394-e920-4131-be48-b15d92c3c32d
wandb_project: 07a
wandb_run: your_name
wandb_runid: a0005394-e920-4131-be48-b15d92c3c32d
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null

4f0bc850-8791-4641-9ae4-1a1482df5a4d

This model is a fine-tuned version of numind/NuExtract-v1.5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8201

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: 0.000207
• train_batch_size: 4
• eval_batch_size: 4
• seed: 70
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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: 100
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	3.5961
8.123	0.1914	500	1.0323
7.3353	0.3829	1000	0.9058
6.8517	0.5743	1500	0.8326
6.6975	0.7657	2000	0.8201

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1