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: 0.0086

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
2.7015	1.0	6	2.0207
1.7126	2.0	12	1.2868
1.1107	3.0	18	0.9127
0.8465	4.0	24	0.7797
0.749	5.0	30	0.7586
0.71	6.0	36	0.6566
0.6332	7.0	42	0.6026
0.5757	8.0	48	0.5232
0.5054	9.0	54	0.4744
0.4469	10.0	60	0.3915
0.3736	11.0	66	0.3214
0.314	12.0	72	0.2855
0.282	13.0	78	0.2260
0.2234	14.0	84	0.2077
0.2157	15.0	90	0.1623
0.1647	16.0	96	0.1344
0.1505	17.0	102	0.1246
0.1342	18.0	108	0.1086
0.1104	19.0	114	0.0998
0.098	20.0	120	0.0788
0.0829	21.0	126	0.0575
0.0706	22.0	132	0.0496
0.0639	23.0	138	0.0425
0.0544	24.0	144	0.0352
0.0478	25.0	150	0.0316
0.0435	26.0	156	0.0255
0.0368	27.0	162	0.0237
0.0314	28.0	168	0.0215
0.0313	29.0	174	0.0175
0.0281	30.0	180	0.0157
0.0319	31.0	186	0.0132
0.0235	32.0	192	0.0117
0.0207	33.0	198	0.0112
0.0178	34.0	204	0.0104
0.0184	35.0	210	0.0098
0.0176	36.0	216	0.0092
0.0161	37.0	222	0.0092
0.0167	38.0	228	0.0090
0.0154	39.0	234	0.0087
0.0155	40.0	240	0.0086

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2