Hugging Face's logo

lesso13
/
ec902335-a828-43c8-ab11-316a9974bb0c

PEFT
Safetensors
gptj
axolotl
Generated from Trainer
Model card Files Community
ec902335-a828-43c8-ab11-316a9974bb0c / README.md
lesso13's picture
lesso13
End of training
fec959e verified
preview code
|
raw
history blame contribute delete
1.82 kB
metadata
library_name: peft
base_model: furiosa-ai/mlperf-gpt-j-6b
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: ec902335-a828-43c8-ab11-316a9974bb0c
    results: []

Built with Axolotl

ec902335-a828-43c8-ab11-316a9974bb0c

This model is a fine-tuned version of furiosa-ai/mlperf-gpt-j-6b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0656

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: 0.000213
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 130
  • 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: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0009 1 1.3000
0.5274 0.4651 500 0.0656

Framework versions

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