codet5p-770m-2
This model is a fine-tuned version of Salesforce/codet5p-770m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1083
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5059 | 0.9971 | 85 | 0.1362 |
0.1474 | 1.9941 | 170 | 0.1209 |
0.1352 | 2.9912 | 255 | 0.1157 |
0.1259 | 4.0 | 341 | 0.1132 |
0.1224 | 4.9971 | 426 | 0.1105 |
0.117 | 5.9941 | 511 | 0.1096 |
0.1128 | 6.9912 | 596 | 0.1087 |
0.1084 | 8.0 | 682 | 0.1072 |
0.1065 | 8.9971 | 767 | 0.1075 |
0.1077 | 9.9941 | 852 | 0.1071 |
0.1013 | 10.9912 | 937 | 0.1074 |
0.0981 | 12.0 | 1023 | 0.1073 |
0.098 | 12.9971 | 1108 | 0.1078 |
0.097 | 13.9941 | 1193 | 0.1082 |
0.0952 | 14.9560 | 1275 | 0.1083 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 22