calculator_model_test

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

• Loss: 0.6527

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: 0.001
• train_batch_size: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.6778	1.0	6	3.1191
2.7094	2.0	12	2.1966
1.9597	3.0	18	1.7446
1.7331	4.0	24	1.6583
1.5938	5.0	30	1.6425
1.5338	6.0	36	1.5592
1.5077	7.0	42	1.5055
1.4896	8.0	48	1.4880
1.4419	9.0	54	1.4727
1.4062	10.0	60	1.3960
1.3459	11.0	66	1.3129
1.2961	12.0	72	1.3037
1.2268	13.0	78	1.2964
1.2251	14.0	84	1.1677
1.1559	15.0	90	1.1312
1.1157	16.0	96	1.1714
1.1385	17.0	102	1.1348
1.0996	18.0	108	1.1113
1.0407	19.0	114	0.9871
0.9734	20.0	120	0.9324
0.9512	21.0	126	0.9743
0.951	22.0	132	0.9441
0.917	23.0	138	0.8909
0.8726	24.0	144	0.9193
0.8937	25.0	150	0.8686
0.8351	26.0	156	0.8182
0.8397	27.0	162	0.7957
0.8148	28.0	168	0.7851
0.7866	29.0	174	0.7707
0.7579	30.0	180	0.7610
0.7516	31.0	186	0.7259
0.734	32.0	192	0.7193
0.7375	33.0	198	0.7392
0.7284	34.0	204	0.7019
0.7283	35.0	210	0.6881
0.6968	36.0	216	0.6745
0.69	37.0	222	0.6672
0.6877	38.0	228	0.6606
0.6741	39.0	234	0.6575
0.6741	40.0	240	0.6527

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2