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: 0.1333

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
2.9526	1.0	6	2.2864
2.0549	2.0	12	1.7909
1.6519	3.0	18	1.4416
1.3484	4.0	24	1.2007
1.1103	5.0	30	1.0371
0.9763	6.0	36	0.9188
0.8829	7.0	42	0.8155
0.7861	8.0	48	0.7443
0.733	9.0	54	0.7678
0.7173	10.0	60	0.6706
0.6693	11.0	66	0.6274
0.6285	12.0	72	0.6015
0.5992	13.0	78	0.5695
0.5559	14.0	84	0.5178
0.5266	15.0	90	0.4944
0.5091	16.0	96	0.4834
0.5115	17.0	102	0.4531
0.4719	18.0	108	0.4386
0.4503	19.0	114	0.4231
0.4237	20.0	120	0.4014
0.439	21.0	126	0.4088
0.3869	22.0	132	0.3689
0.3628	23.0	138	0.3634
0.3625	24.0	144	0.3437
0.3284	25.0	150	0.3134
0.3139	26.0	156	0.2997
0.3062	27.0	162	0.2816
0.2978	28.0	168	0.2593
0.2754	29.0	174	0.2343
0.2443	30.0	180	0.2220
0.2433	31.0	186	0.2064
0.2232	32.0	192	0.1869
0.2157	33.0	198	0.1824
0.2129	34.0	204	0.1657
0.1871	35.0	210	0.1605
0.1836	36.0	216	0.1520
0.1816	37.0	222	0.1456
0.1652	38.0	228	0.1377
0.1903	39.0	234	0.1338
0.1713	40.0	240	0.1333

Framework versions

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