codeparrot-ds
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3380
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 |
---|---|---|---|
2.7268 | 0.0766 | 5000 | 2.0903 |
1.8879 | 0.1533 | 10000 | 1.8917 |
1.736 | 0.2299 | 15000 | 1.7960 |
1.6529 | 0.3065 | 20000 | 1.7344 |
1.5904 | 0.3832 | 25000 | 1.6852 |
1.5397 | 0.4598 | 30000 | 1.6280 |
1.4955 | 0.5365 | 35000 | 1.5907 |
1.4507 | 0.6131 | 40000 | 1.5538 |
1.4103 | 0.6897 | 45000 | 1.5098 |
1.3687 | 0.7664 | 50000 | 1.4685 |
1.3315 | 0.8430 | 55000 | 1.4236 |
1.2884 | 0.9196 | 60000 | 1.3930 |
1.2449 | 0.9963 | 65000 | 1.3380 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.1.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 5