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: 0.0085

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.9669	1.0	6	0.6731
0.4986	2.0	12	0.3548
0.3213	3.0	18	0.2928
0.2867	4.0	24	0.2126
0.2162	5.0	30	0.1518
0.167	6.0	36	0.1237
0.1443	7.0	42	0.0969
0.1235	8.0	48	0.0684
0.1002	9.0	54	0.0610
0.0928	10.0	60	0.0616
0.0843	11.0	66	0.0507
0.0737	12.0	72	0.0435
0.0606	13.0	78	0.0387
0.0583	14.0	84	0.0363
0.0529	15.0	90	0.0278
0.0515	16.0	96	0.0267
0.0539	17.0	102	0.0263
0.0514	18.0	108	0.0312
0.0498	19.0	114	0.0248
0.0405	20.0	120	0.0252
0.0376	21.0	126	0.0242
0.0417	22.0	132	0.0279
0.0361	23.0	138	0.0219
0.0327	24.0	144	0.0152
0.0288	25.0	150	0.0146
0.0253	26.0	156	0.0162
0.0223	27.0	162	0.0140
0.0207	28.0	168	0.0118
0.0198	29.0	174	0.0108
0.0191	30.0	180	0.0109
0.0172	31.0	186	0.0096
0.0165	32.0	192	0.0093
0.0153	33.0	198	0.0091
0.0156	34.0	204	0.0092
0.0159	35.0	210	0.0092
0.0153	36.0	216	0.0088
0.0157	37.0	222	0.0085
0.0149	38.0	228	0.0084
0.0135	39.0	234	0.0086
0.0135	40.0	240	0.0085

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.20.3