metadata
license: bsd-3-clause
base_model: Salesforce/codegen-350M-mono
tags:
- generated_from_trainer
model-index:
- name: ast_method2test-codegen-350M_v1_v1
results: []
ast_method2test-codegen-350M_v1_v1
This model is a fine-tuned version of Salesforce/codegen-350M-mono on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2259
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2695 | 1.0 | 1768 | 0.2096 |
| 0.1801 | 2.0 | 3536 | 0.1897 |
| 0.1479 | 3.0 | 5304 | 0.1855 |
| 0.1245 | 4.0 | 7072 | 0.1904 |
| 0.1073 | 5.0 | 8840 | 0.1961 |
| 0.0941 | 6.0 | 10608 | 0.2011 |
| 0.0831 | 7.0 | 12376 | 0.2081 |
| 0.074 | 8.0 | 14144 | 0.2157 |
| 0.0667 | 9.0 | 15912 | 0.2209 |
| 0.0612 | 10.0 | 17680 | 0.2259 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0