fresh-2-layer-copa

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3801
• Accuracy: 0.2980

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 321
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	1.3862	0.2071
No log	2.0	126	1.3862	0.2071
No log	3.0	189	1.3862	0.2525
No log	4.0	252	1.3862	0.2374
No log	5.0	315	1.3859	0.2626
No log	6.0	378	1.3863	0.2071
No log	7.0	441	1.3865	0.2778
0.6953	8.0	504	1.3861	0.2778
0.6953	9.0	567	1.3857	0.2071
0.6953	10.0	630	1.3859	0.2525
0.6953	11.0	693	1.3863	0.2475
0.6953	12.0	756	1.3863	0.2778
0.6953	13.0	819	1.3863	0.2576
0.6953	14.0	882	1.3834	0.2778
0.6953	15.0	945	1.3865	0.2576
0.6897	16.0	1008	1.3856	0.2677
0.6897	17.0	1071	1.3912	0.2273
0.6897	18.0	1134	1.3801	0.2980
0.6897	19.0	1197	1.3878	0.2020
0.6897	20.0	1260	1.3961	0.2525

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.0