Hugging Face's logo

stojchet
/
dpo1-sft1

Text Generation
Transformers
Safetensors
llama
trl
sft
Generated from Trainer
text-generation-inference
Model card Files Community
dpo1-sft1 / README.md
stojchet's picture
stojchet
End of training
6967541 verified
preview code
|
raw
history blame contribute delete
1.39 kB
metadata
library_name: transformers
license: other
base_model: stojchet/dpo1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: dpo1-sft1
    results: []

dpo1-sft1

This model is a fine-tuned version of stojchet/dpo1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 13.2064

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
14.11 2.3088 100 13.2064

Framework versions

  • Transformers 4.45.0
  • Pytorch 2.5.1+cu124
  • Datasets 2.19.2
  • Tokenizers 0.20.3