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: 0.7518

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
3.392	1.0	6	2.7421
2.3678	2.0	12	1.9842
1.8103	3.0	18	1.6702
1.6444	4.0	24	1.5900
1.5998	5.0	30	1.5549
1.6759	6.0	36	1.5762
1.5344	7.0	42	1.5907
1.5276	8.0	48	1.5784
1.5187	9.0	54	1.5224
1.5007	10.0	60	1.4601
1.4285	11.0	66	1.4192
1.3919	12.0	72	1.3792
1.3663	13.0	78	1.3728
1.3035	14.0	84	1.2453
1.2542	15.0	90	1.2191
1.2343	16.0	96	1.1600
1.1959	17.0	102	1.1465
1.1617	18.0	108	1.0958
1.1189	19.0	114	1.0729
1.1026	20.0	120	1.1611
1.1227	21.0	126	1.0368
1.0386	22.0	132	1.0107
0.9962	23.0	138	0.9677
0.9762	24.0	144	0.9360
0.9474	25.0	150	0.9168
0.9317	26.0	156	0.9569
0.9156	27.0	162	0.9376
0.9061	28.0	168	0.9363
0.9147	29.0	174	0.9067
0.9141	30.0	180	0.8845
0.8753	31.0	186	0.8666
0.8572	32.0	192	0.8369
0.848	33.0	198	0.8324
0.8231	34.0	204	0.7965
0.8167	35.0	210	0.7844
0.8004	36.0	216	0.7741
0.7786	37.0	222	0.7700
0.8023	38.0	228	0.7571
0.7799	39.0	234	0.7593
0.7947	40.0	240	0.7518

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2