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: 0.1029

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
3.0054	1.0	6	2.2737
2.0384	2.0	12	1.7426
1.5809	3.0	18	1.3404
1.2444	4.0	24	1.0828
1.0174	5.0	30	0.9111
0.8686	6.0	36	0.7906
0.7634	7.0	42	0.7097
0.7201	8.0	48	0.6570
0.6563	9.0	54	0.6026
0.6174	10.0	60	0.5597
0.5637	11.0	66	0.5282
0.5339	12.0	72	0.5110
0.5056	13.0	78	0.4819
0.4833	14.0	84	0.4364
0.4595	15.0	90	0.4270
0.4414	16.0	96	0.4014
0.4358	17.0	102	0.3982
0.3998	18.0	108	0.3680
0.3790	19.0	114	0.3431
0.3564	20.0	120	0.3411
0.3567	21.0	126	0.3193
0.3297	22.0	132	0.2895
0.3156	23.0	138	0.2718
0.2846	24.0	144	0.2467
0.2590	25.0	150	0.2285
0.2476	26.0	156	0.2163
0.2361	27.0	162	0.2084
0.2255	28.0	168	0.1900
0.2156	29.0	174	0.1825
0.2100	30.0	180	0.1861
0.2060	31.0	186	0.1727
0.1867	32.0	192	0.1626
0.1811	33.0	198	0.1422
0.1652	34.0	204	0.1297
0.1540	35.0	210	0.1264
0.1483	36.0	216	0.1190
0.1493	37.0	222	0.1116
0.1373	38.0	228	0.1065
0.1366	39.0	234	0.1040
0.1319	40.0	240	0.1029

Framework versions

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