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: 0.1663

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
3.0776	1.0	5	2.3467
2.1508	2.0	10	1.8830
1.7317	3.0	15	1.5145
1.3813	4.0	20	1.1827
1.1212	5.0	25	0.9861
0.946	6.0	30	0.8613
0.8189	7.0	35	0.7596
0.7274	8.0	40	0.6659
0.6581	9.0	45	0.6032
0.6222	10.0	50	0.5788
0.5988	11.0	55	0.5530
0.5561	12.0	60	0.5159
0.5173	13.0	65	0.4937
0.4961	14.0	70	0.4725
0.4748	15.0	75	0.4424
0.4517	16.0	80	0.4525
0.4394	17.0	85	0.4096
0.4145	18.0	90	0.3804
0.3882	19.0	95	0.3678
0.3736	20.0	100	0.3467
0.3562	21.0	105	0.3246
0.3406	22.0	110	0.3180
0.3231	23.0	115	0.2966
0.3111	24.0	120	0.2839
0.2992	25.0	125	0.2701
0.2815	26.0	130	0.2644
0.2753	27.0	135	0.2459
0.2651	28.0	140	0.2375
0.2532	29.0	145	0.2226
0.2407	30.0	150	0.2142
0.2339	31.0	155	0.2031
0.2218	32.0	160	0.1959
0.2142	33.0	165	0.1880
0.2107	34.0	170	0.1871
0.2062	35.0	175	0.1816
0.1997	36.0	180	0.1789
0.1961	37.0	185	0.1740
0.1929	38.0	190	0.1707
0.1907	39.0	195	0.1681
0.1885	40.0	200	0.1663

Framework versions

• Transformers 4.39.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2