metadata
tags:
- generated_from_trainer
model-index:
- name: codeparrot-ds
results: []
codeparrot-ds
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1005
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 |
|---|---|---|---|
| 2.628 | 0.0766 | 5000 | 1.9111 |
| 1.7546 | 0.1533 | 10000 | 1.6929 |
| 1.6004 | 0.2299 | 15000 | 1.5822 |
| 1.5131 | 0.3065 | 20000 | 1.5084 |
| 1.4467 | 0.3832 | 25000 | 1.4519 |
| 1.3917 | 0.4598 | 30000 | 1.4033 |
| 1.3427 | 0.5365 | 35000 | 1.3530 |
| 1.293 | 0.6131 | 40000 | 1.3065 |
| 1.2472 | 0.6897 | 45000 | 1.2618 |
| 1.2003 | 0.7664 | 50000 | 1.2165 |
| 1.1583 | 0.8430 | 55000 | 1.1735 |
| 1.1135 | 0.9196 | 60000 | 1.1337 |
| 1.0763 | 0.9963 | 65000 | 1.1005 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.1.0
- Datasets 2.19.1
- Tokenizers 0.19.1