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: 0.0711

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
3.0159	1.0	6	2.2518
2.0167	2.0	12	1.7338
1.5432	3.0	18	1.3138
1.2049	4.0	24	1.0937
1.0595	5.0	30	1.0223
0.9257	6.0	36	0.8429
0.7962	7.0	42	0.7254
0.6995	8.0	48	0.6610
0.6407	9.0	54	0.6106
0.6006	10.0	60	0.5774
0.5709	11.0	66	0.5271
0.5281	12.0	72	0.5033
0.5240	13.0	78	0.5112
0.5037	14.0	84	0.4516
0.4613	15.0	90	0.4711
0.4576	16.0	96	0.4196
0.4247	17.0	102	0.3958
0.3944	18.0	108	0.3781
0.3636	19.0	114	0.3461
0.3407	20.0	120	0.3095
0.3060	21.0	126	0.2803
0.2823	22.0	132	0.2655
0.2724	23.0	138	0.2299
0.2348	24.0	144	0.2070
0.2169	25.0	150	0.1734
0.1905	26.0	156	0.1519
0.1736	27.0	162	0.1474
0.1666	28.0	168	0.1242
0.1507	29.0	174	0.1131
0.1312	30.0	180	0.1065
0.1315	31.0	186	0.0964
0.1220	32.0	192	0.0893
0.1144	33.0	198	0.0862
0.1057	34.0	204	0.0830
0.1046	35.0	210	0.0817
0.1009	36.0	216	0.0770
0.0977	37.0	222	0.0765
0.0948	38.0	228	0.0736
0.0930	39.0	234	0.0719
0.0903	40.0	240	0.0711

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2