Hugging Face's logo

Best000
/
32c9118c-9ab2-462a-986b-cb14498ab6d6

PEFT
Safetensors
opt
axolotl
Generated from Trainer
Model card Files Community
32c9118c-9ab2-462a-986b-cb14498ab6d6 / README.md
Best000's picture
Best000
End of training
ae67d9c verified
preview code
|
raw
history blame
4.26 kB
metadata
library_name: peft
license: other
base_model: facebook/opt-350m
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 32c9118c-9ab2-462a-986b-cb14498ab6d6
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: facebook/opt-350m
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f09a068a17c73549_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f09a068a17c73549_train_data.json
  type:
    field_instruction: prompt
    field_output: gold_standard_solution
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 300
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: Best000/32c9118c-9ab2-462a-986b-cb14498ab6d6
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 17996
micro_batch_size: 4
mlflow_experiment_name: /tmp/f09a068a17c73549_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 300
saves_per_epoch: null
sequence_len: 512
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: fb6671a1-3169-4044-b339-5b07d92c1691
wandb_project: SN56-15
wandb_run: your_name
wandb_runid: fb6671a1-3169-4044-b339-5b07d92c1691
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

32c9118c-9ab2-462a-986b-cb14498ab6d6

This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 4.9687

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 50
  • training_steps: 17996

Training results

Training Loss Epoch Step Validation Loss
No log 0.0003 1 5.0216
11.4064 0.0847 300 4.2782
11.3498 0.1695 600 4.2733
10.8428 0.2542 900 3.5935
10.9353 0.3390 1200 3.9772
11.1807 0.4237 1500 3.5348
11.3266 0.5085 1800 3.3175
10.7106 0.5932 2100 3.5059
10.5636 0.6780 2400 3.9275
10.635 0.7627 2700 4.9687

Framework versions

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