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: 0.6619

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

Training results

Training Loss	Epoch	Step	Validation Loss
3.3473	1.0	6	2.7247
2.3527	2.0	12	1.9354
1.825	3.0	18	1.6728
1.6407	4.0	24	1.5858
1.5855	5.0	30	1.5447
1.5394	6.0	36	1.5319
1.534	7.0	42	1.5225
1.5094	8.0	48	1.5909
1.5007	9.0	54	1.4836
1.485	10.0	60	1.4084
1.378	11.0	66	1.5103
1.4233	12.0	72	1.3968
1.3443	13.0	78	1.3014
1.3112	14.0	84	1.2836
1.2276	15.0	90	1.1906
1.1665	16.0	96	1.1611
1.1533	17.0	102	1.0644
1.0948	18.0	108	1.0426
1.0375	19.0	114	1.0362
1.0114	20.0	120	0.9836
1.0002	21.0	126	0.9499
0.9633	22.0	132	0.8812
0.923	23.0	138	0.8850
0.9197	24.0	144	0.8646
0.875	25.0	150	0.8264
0.8645	26.0	156	0.8182
0.8398	27.0	162	0.7980
0.8313	28.0	168	0.7804
0.7947	29.0	174	0.7572
0.7929	30.0	180	0.7846
0.7809	31.0	186	0.7695
0.7655	32.0	192	0.7372
0.7692	33.0	198	0.7230
0.7658	34.0	204	0.7236
0.7587	35.0	210	0.7068
0.7389	36.0	216	0.6952
0.7244	37.0	222	0.6792
0.7087	38.0	228	0.6692
0.7031	39.0	234	0.6634
0.7026	40.0	240	0.6619

Framework versions

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