metadata
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- generated_from_trainer
model-index:
- name: codet5-small-v24
results: []
codet5-small-v24
This model is a fine-tuned version of Salesforce/codet5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5010
- Bleu Score: 0.0015
- Gen Len: 14.1585
Model description
tarined on,
- dataset: chathuranga-jayanath/context-5-finmath-times4j-html-mavendoxia-wro4j-guava-supercsv-len-10000-prompt-0
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: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
|---|---|---|---|---|---|
| 0.7694 | 1.0 | 3752 | 0.6072 | 0.0015 | 14.1039 |
| 0.6301 | 2.0 | 7504 | 0.5222 | 0.0015 | 14.129 |
| 0.5463 | 3.0 | 11256 | 0.5010 | 0.0015 | 14.1585 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1