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: 0.6281

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
3.3788	1.0	6	2.7190
2.3329	2.0	12	1.9212
1.7962	3.0	18	1.6430
1.5944	4.0	24	1.5778
1.5824	5.0	30	1.5569
1.5513	6.0	36	1.5152
1.5044	7.0	42	1.5108
1.4601	8.0	48	1.4058
1.3676	9.0	54	1.3091
1.3608	10.0	60	1.3141
1.2438	11.0	66	1.1829
1.1594	12.0	72	1.1139
1.0901	13.0	78	1.0550
1.1289	14.0	84	1.1184
1.1028	15.0	90	0.9935
0.9901	16.0	96	1.1129
1.0213	17.0	102	0.9731
0.9919	18.0	108	0.9129
0.9487	19.0	114	0.9160
0.9437	20.0	120	0.8889
0.8907	21.0	126	0.8633
0.8628	22.0	132	0.8779
0.8722	23.0	138	0.8225
0.8261	24.0	144	0.8049
0.823	25.0	150	0.8250
0.8272	26.0	156	0.8704
0.8194	27.0	162	0.7511
0.7772	28.0	168	0.7401
0.7539	29.0	174	0.7332
0.7464	30.0	180	0.7092
0.7485	31.0	186	0.6996
0.7214	32.0	192	0.6817
0.6968	33.0	198	0.6742
0.6903	34.0	204	0.6703
0.6846	35.0	210	0.6723
0.6845	36.0	216	0.6492
0.6784	37.0	222	0.6416
0.672	38.0	228	0.6367
0.6639	39.0	234	0.6306
0.6682	40.0	240	0.6281

Framework versions

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