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: 0.0653

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
3.0601	1.0	5	2.3320
2.1438	2.0	10	1.8625
1.719	3.0	15	1.4731
1.3536	4.0	20	1.1824
1.1078	5.0	25	1.0030
0.9378	6.0	30	0.8243
0.814	7.0	35	0.7440
0.7285	8.0	40	0.6701
0.6557	9.0	45	0.5971
0.6103	10.0	50	0.5747
0.5812	11.0	55	0.5327
0.5484	12.0	60	0.5351
0.5322	13.0	65	0.4831
0.485	14.0	70	0.4645
0.4599	15.0	75	0.4106
0.4148	16.0	80	0.3721
0.3847	17.0	85	0.3418
0.3717	18.0	90	0.3214
0.3406	19.0	95	0.3021
0.3133	20.0	100	0.2631
0.2902	21.0	105	0.2421
0.2558	22.0	110	0.2098
0.2351	23.0	115	0.1821
0.2115	24.0	120	0.1597
0.1909	25.0	125	0.1435
0.1745	26.0	130	0.1364
0.1612	27.0	135	0.1223
0.1516	28.0	140	0.1127
0.1379	29.0	145	0.1012
0.1281	30.0	150	0.0945
0.1232	31.0	155	0.0858
0.1153	32.0	160	0.0822
0.1077	33.0	165	0.0798
0.1039	34.0	170	0.0764
0.1025	35.0	175	0.0719
0.0989	36.0	180	0.0685
0.0955	37.0	185	0.0685
0.0949	38.0	190	0.0660
0.0915	39.0	195	0.0653
0.0901	40.0	200	0.0653

Framework versions

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