metadata
library_name: peft
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: Se124M10KInfPrompt_WT_EOS
results: []
Se124M10KInfPrompt_WT_EOS
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0978
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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_ratio: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2645 | 0.5970 | 20 | 2.8750 |
| 3.0103 | 1.1791 | 40 | 2.6534 |
| 2.7014 | 1.7761 | 60 | 2.3720 |
| 2.3851 | 2.3582 | 80 | 2.1090 |
| 2.1288 | 2.9552 | 100 | 1.8650 |
| 1.9062 | 3.5373 | 120 | 1.6703 |
| 1.739 | 4.1194 | 140 | 1.5153 |
| 1.6033 | 4.7164 | 160 | 1.3879 |
| 1.5039 | 5.2985 | 180 | 1.2845 |
| 1.4219 | 5.8955 | 200 | 1.2122 |
| 1.357 | 6.4776 | 220 | 1.1649 |
| 1.3201 | 7.0597 | 240 | 1.1304 |
| 1.2923 | 7.6567 | 260 | 1.1101 |
| 1.2831 | 8.2388 | 280 | 1.1035 |
| 1.2715 | 8.8358 | 300 | 1.1007 |
| 1.2721 | 9.4179 | 320 | 1.0986 |
Framework versions
- PEFT 0.15.1
- Transformers 4.51.3
- Pytorch 2.6.0+cu118
- Datasets 3.5.0
- Tokenizers 0.21.1