metadata
library_name: transformers
license: mit
base_model: EleutherAI/gpt-neo-125M
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: MD5_gpt_neo_v2.0
results: []
MD5_gpt_neo_v2.0
This model is a fine-tuned version of EleutherAI/gpt-neo-125M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0286
- Rouge1: 0.0108
- Rouge2: 0.0
- Rougel: 0.0108
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| 25.8979 | 1.0 | 3438 | 8.3873 | 0.0224 | 0.0020 | 0.0194 |
| 8.0473 | 2.0 | 6876 | 2.5482 | 0.0137 | 0.0 | 0.0137 |
| 9.4131 | 3.0 | 10314 | 2.2991 | 0.0576 | 0.0 | 0.0601 |
| 5.4755 | 4.0 | 13752 | 0.8236 | 0.0 | 0.0 | 0.0 |
| 6.1776 | 5.0 | 17190 | 1.0286 | 0.0108 | 0.0 | 0.0108 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1