Hugging Face's logo

lesso10
/
4f58aa07-d05e-4f5c-b0f1-21e14376ac9b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
4f58aa07-d05e-4f5c-b0f1-21e14376ac9b / README.md
lesso10's picture
lesso10
End of training
2883b0e verified
preview code
|
raw
history blame contribute delete
1.97 kB
metadata
library_name: peft
license: llama2
base_model: lmsys/vicuna-13b-v1.5
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 4f58aa07-d05e-4f5c-b0f1-21e14376ac9b
    results: []

Built with Axolotl

4f58aa07-d05e-4f5c-b0f1-21e14376ac9b

This model is a fine-tuned version of lmsys/vicuna-13b-v1.5 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6298

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: 0.00021
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • 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: 50
  • training_steps: 231

Training results

Training Loss Epoch Step Validation Loss
No log 0.0043 1 2.4689
2.0403 0.2169 50 2.1299
2.0103 0.4338 100 1.9008
1.8141 0.6508 150 1.7426
1.9809 0.8677 200 1.6298

Framework versions

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