metadata
library_name: transformers
license: mit
base_model: gpt2
tags:
- Text generation
- generated_from_trainer
model-index:
- name: codeparrot-ds-2
results: []
codeparrot-ds-2
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0614
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5681 | 0.0766 | 5000 | 1.7468 |
| 1.6828 | 0.1533 | 10000 | 1.5245 |
| 1.5337 | 0.2299 | 15000 | 1.4208 |
| 1.4542 | 0.3065 | 20000 | 1.3556 |
| 1.3941 | 0.3832 | 25000 | 1.3040 |
| 1.3429 | 0.4598 | 30000 | 1.2564 |
| 1.2972 | 0.5365 | 35000 | 1.2130 |
| 1.2508 | 0.6131 | 40000 | 1.1707 |
| 1.21 | 0.6897 | 45000 | 1.1323 |
| 1.1723 | 0.7664 | 50000 | 1.0998 |
| 1.1453 | 0.8430 | 55000 | 1.0765 |
| 1.1239 | 0.9196 | 60000 | 1.0645 |
| 1.1165 | 0.9963 | 65000 | 1.0614 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1