metadata
license: bsd-3-clause
base_model: Salesforce/codet5-large
tags:
- generated_from_trainer
datasets:
- arrow
library_name: peft
model-index:
- name: codet5-large-2024-11-27_20-00
results: []
codet5-large-2024-11-27_20-00
This model is a fine-tuned version of Salesforce/codet5-large on the arrow dataset. It achieves the following results on the evaluation set:
- Loss: 0.2856
- Gen Len: 18.9997
- Bertscorer-p: 0.6071
- Bertscorer-r: 0.2214
- Bertscorer-f1: 0.4073
- Sacrebleu-score: 13.1915
- Sacrebleu-precisions: [91.2377160786171, 81.28148602080365, 74.45810305941498, 69.5812750161697]
- Bleu-bp: 0.1676
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Gen Len | Bertscorer-p | Bertscorer-r | Bertscorer-f1 | Sacrebleu-score | Sacrebleu-precisions | Bleu-bp |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.3327 | 1.0 | 2386 | 0.2856 | 18.9997 | 0.6071 | 0.2214 | 0.4073 | 13.1915 | [91.2377160786171, 81.28148602080365, 74.45810305941498, 69.5812750161697] | 0.1676 |
Framework versions
- PEFT 0.13.2
- Transformers 4.40.1
- Pytorch 1.13.1+cu117
- Datasets 3.1.0
- Tokenizers 0.19.1