fresh-2-layer-piqa-distill-of-fresh-2-layer-gpqa

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

• Loss: 16.0175
• Accuracy: 0.3586

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	18.2723	0.2273
No log	2.0	126	15.2877	0.2576
No log	3.0	189	16.4507	0.3131
No log	4.0	252	13.5118	0.3485
No log	5.0	315	13.6895	0.3384
No log	6.0	378	15.5376	0.3182
No log	7.0	441	17.7696	0.3182
2.8866	8.0	504	14.3626	0.3232
2.8866	9.0	567	15.1187	0.3232
2.8866	10.0	630	16.8223	0.3384
2.8866	11.0	693	16.0992	0.3081
2.8866	12.0	756	15.7492	0.3283
2.8866	13.0	819	14.8661	0.3485
2.8866	14.0	882	16.7236	0.3485
2.8866	15.0	945	16.0175	0.3586
0.4396	16.0	1008	15.5002	0.3333
0.4396	17.0	1071	16.1226	0.3586
0.4396	18.0	1134	16.3226	0.3232
0.4396	19.0	1197	16.2413	0.3434
0.4396	20.0	1260	16.0952	0.3384

Framework versions

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