entailedpolarity_-gpt2-a2b2l0.001

This model was trained from scratch on the bigbench dataset. It achieves the following results on the evaluation set:

• Loss: 8.8419
• Accuracy: 0.2083

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	6	8.8417	0.2083
No log	2.0	12	8.8339	0.2083
No log	3.0	18	7.9904	0.2917
No log	4.0	24	4.6119	0.75
No log	5.0	30	8.8414	0.2083
No log	6.0	36	8.8424	0.2083
No log	7.0	42	8.8427	0.2083
No log	8.0	48	8.8417	0.2083
No log	9.0	54	8.8450	0.2083
No log	10.0	60	8.8422	0.2083
No log	11.0	66	8.8429	0.2083
No log	12.0	72	8.8432	0.2083
No log	13.0	78	8.8430	0.2083
No log	14.0	84	8.8415	0.2083
No log	15.0	90	8.8431	0.2083
No log	16.0	96	8.8425	0.2083
No log	17.0	102	8.8431	0.2083
No log	18.0	108	8.8454	0.2083
No log	19.0	114	8.8430	0.2083
No log	20.0	120	8.8419	0.2083

Framework versions

• Transformers 4.37.0
• Pytorch 1.13.1+cu117
• Datasets 2.15.0
• Tokenizers 0.15.2