metadata
library_name: peft
license: mit
base_model: EleutherAI/gpt-neo-125m
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 080df56e-0c26-4dfe-8721-4e500be28a95
results: []
080df56e-0c26-4dfe-8721-4e500be28a95
This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2607
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: 2
- eval_batch_size: 2
- seed: 170
- gradient_accumulation_steps: 4
- 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: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 2.4225 |
| 9.0492 | 0.0076 | 50 | 2.3960 |
| 9.8507 | 0.0151 | 100 | 2.3403 |
| 9.5135 | 0.0227 | 150 | 2.3134 |
| 9.2993 | 0.0302 | 200 | 2.2947 |
| 9.1432 | 0.0378 | 250 | 2.2810 |
| 9.3859 | 0.0453 | 300 | 2.2717 |
| 9.5146 | 0.0529 | 350 | 2.2661 |
| 8.8903 | 0.0604 | 400 | 2.2625 |
| 9.3279 | 0.0680 | 450 | 2.2614 |
| 9.336 | 0.0755 | 500 | 2.2607 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1