calculator_model_test_with_steps

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0782

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
2.3166	1.0	6	1.7843
1.6117	2.0	12	1.4283
1.3630	3.0	18	1.2932
1.2278	4.0	24	1.1252
1.0568	5.0	30	0.9816
0.9235	6.0	36	0.8970
0.8544	7.0	42	0.8140
0.7859	8.0	48	0.7258
0.7176	9.0	54	0.6732
0.6560	10.0	60	0.6337
0.6114	11.0	66	0.5447
0.5682	12.0	72	0.4996
0.5219	13.0	78	0.5244
0.5037	14.0	84	0.4369
0.4572	15.0	90	0.4172
0.4312	16.0	96	0.3730
0.3958	17.0	102	0.3966
0.4204	18.0	108	0.3818
0.3960	19.0	114	0.3489
0.3695	20.0	120	0.3186
0.3458	21.0	126	0.3016
0.3137	22.0	132	0.2860
0.3133	23.0	138	0.2519
0.2819	24.0	144	0.2399
0.2685	25.0	150	0.2222
0.2570	26.0	156	0.1930
0.2389	27.0	162	0.2000
0.2348	28.0	168	0.1874
0.2193	29.0	174	0.1636
0.2052	30.0	180	0.1454
0.2008	31.0	186	0.1367
0.1890	32.0	192	0.1380
0.1886	33.0	198	0.1192
0.1737	34.0	204	0.1071
0.1589	35.0	210	0.1030
0.1528	36.0	216	0.0939
0.1415	37.0	222	0.0864
0.1417	38.0	228	0.0842
0.1282	39.0	234	0.0804
0.1318	40.0	240	0.0782

Framework versions

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