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: 0.0455

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
2.7845	1.0	6	2.1181
1.8407	2.0	12	1.5060
1.2932	3.0	18	1.0056
0.8986	4.0	24	0.8024
0.741	5.0	30	0.7078
0.6482	6.0	36	0.5938
0.5563	7.0	42	0.5336
0.498	8.0	48	0.4787
0.4542	9.0	54	0.4216
0.4078	10.0	60	0.4064
0.3819	11.0	66	0.3621
0.3536	12.0	72	0.3261
0.318	13.0	78	0.2967
0.2913	14.0	84	0.2793
0.2734	15.0	90	0.2498
0.2549	16.0	96	0.2557
0.2541	17.0	102	0.2252
0.2274	18.0	108	0.2301
0.2272	19.0	114	0.2112
0.1963	20.0	120	0.1780
0.1744	21.0	126	0.1734
0.1805	22.0	132	0.1520
0.1599	23.0	138	0.1314
0.1517	24.0	144	0.1364
0.1469	25.0	150	0.1583
0.1524	26.0	156	0.1381
0.1411	27.0	162	0.1048
0.1196	28.0	168	0.0964
0.1095	29.0	174	0.0900
0.1068	30.0	180	0.0798
0.0985	31.0	186	0.0742
0.0897	32.0	192	0.0677
0.0839	33.0	198	0.0638
0.0756	34.0	204	0.0579
0.0771	35.0	210	0.0555
0.0709	36.0	216	0.0507
0.068	37.0	222	0.0482
0.0657	38.0	228	0.0472
0.0661	39.0	234	0.0466
0.0643	40.0	240	0.0455

Framework versions

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