codeparrot-ds
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0623
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 |
---|---|---|---|
2.5658 | 0.08 | 5000 | 1.7437 |
1.6804 | 0.15 | 10000 | 1.5257 |
1.5334 | 0.23 | 15000 | 1.4223 |
1.4536 | 0.31 | 20000 | 1.3574 |
1.3961 | 0.38 | 25000 | 1.3052 |
1.344 | 0.46 | 30000 | 1.2570 |
1.2992 | 0.54 | 35000 | 1.2137 |
1.2533 | 0.61 | 40000 | 1.1730 |
1.2106 | 0.69 | 45000 | 1.1339 |
1.1755 | 0.77 | 50000 | 1.1004 |
1.1442 | 0.84 | 55000 | 1.0772 |
1.1259 | 0.92 | 60000 | 1.0651 |
1.1159 | 1.0 | 65000 | 1.0623 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.0
- Tokenizers 0.15.1
- Downloads last month
- 1