codet5p-220m

This model is a fine-tuned version of Salesforce/codet5p-220m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1124

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: 12
• eval_batch_size: 12
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 24
• 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
0.1963	1.0	175	0.1280
0.1385	2.0	350	0.1227
0.1329	3.0	525	0.1201
0.1288	4.0	700	0.1179
0.126	5.0	875	0.1166
0.1234	6.0	1050	0.1158
0.1216	7.0	1225	0.1145
0.1201	8.0	1400	0.1141
0.1187	9.0	1575	0.1133
0.1177	10.0	1750	0.1130
0.1165	11.0	1925	0.1129
0.1158	12.0	2100	0.1125
0.1151	13.0	2275	0.1125
0.1146	14.0	2450	0.1124
0.1146	15.0	2625	0.1124

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1