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: 0.0741

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
3.0444	1.0	6	2.2982
2.0319	2.0	12	1.7372
1.5871	3.0	18	1.3782
1.2735	4.0	24	1.1017
1.0332	5.0	30	0.9506
0.9051	6.0	36	0.8307
0.7868	7.0	42	0.7057
0.7026	8.0	48	0.6872
0.6729	9.0	54	0.6115
0.6270	10.0	60	0.6062
0.5786	11.0	66	0.5212
0.5293	12.0	72	0.4763
0.4852	13.0	78	0.4490
0.4583	14.0	84	0.4149
0.4152	15.0	90	0.3562
0.3767	16.0	96	0.3472
0.3715	17.0	102	0.3505
0.3611	18.0	108	0.3096
0.3194	19.0	114	0.2867
0.3072	20.0	120	0.2500
0.2794	21.0	126	0.2270
0.2550	22.0	132	0.2257
0.2486	23.0	138	0.2034
0.2315	24.0	144	0.1956
0.2167	25.0	150	0.1968
0.2169	26.0	156	0.1761
0.1939	27.0	162	0.1711
0.1856	28.0	168	0.1356
0.1744	29.0	174	0.1312
0.1595	30.0	180	0.1211
0.1495	31.0	186	0.1110
0.1418	32.0	192	0.0995
0.1329	33.0	198	0.0956
0.1260	34.0	204	0.0909
0.1162	35.0	210	0.0844
0.1135	36.0	216	0.0794
0.1060	37.0	222	0.0777
0.1105	38.0	228	0.0762
0.1032	39.0	234	0.0746
0.1033	40.0	240	0.0741

Framework versions

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