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: 0.1142

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
2.9994	1.0	6	2.3829
2.1071	2.0	12	1.8146
1.6604	3.0	18	1.4548
1.3344	4.0	24	1.2129
1.1057	5.0	30	1.1267
0.9979	6.0	36	0.9518
0.8972	7.0	42	0.8461
0.7958	8.0	48	0.7534
0.7312	9.0	54	0.7009
0.6649	10.0	60	0.6680
0.6393	11.0	66	0.7051
0.6601	12.0	72	0.6567
0.6068	13.0	78	0.5767
0.5647	14.0	84	0.5255
0.4983	15.0	90	0.4750
0.5041	16.0	96	0.4331
0.4763	17.0	102	0.4182
0.4353	18.0	108	0.3774
0.3764	19.0	114	0.3496
0.3449	20.0	120	0.3113
0.3256	21.0	126	0.2987
0.2946	22.0	132	0.2670
0.3009	23.0	138	0.2560
0.2382	24.0	144	0.2373
0.2447	25.0	150	0.2340
0.2641	26.0	156	0.3113
0.2926	27.0	162	0.1925
0.2231	28.0	168	0.1932
0.2826	29.0	174	0.1867
0.1928	30.0	180	0.1672
0.1924	31.0	186	0.1577
0.1727	32.0	192	0.1451
0.1715	33.0	198	0.1365
0.1582	34.0	204	0.1334
0.1606	35.0	210	0.1278
0.1556	36.0	216	0.1282
0.1355	37.0	222	0.1226
0.1305	38.0	228	0.1184
0.1494	39.0	234	0.1148
0.1392	40.0	240	0.1142

Framework versions

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