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: 0.1433

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
2.9812	1.0	6	2.2407
2.0270	2.0	12	1.7466
1.5714	3.0	18	1.2953
1.2001	4.0	24	1.0696
1.0133	5.0	30	0.9091
0.8661	6.0	36	0.7848
0.7555	7.0	42	0.6814
0.6796	8.0	48	0.6318
0.6473	9.0	54	0.6153
0.6041	10.0	60	0.5501
0.5619	11.0	66	0.5469
0.5457	12.0	72	0.5018
0.5004	13.0	78	0.4598
0.4727	14.0	84	0.4299
0.4530	15.0	90	0.4329
0.4326	16.0	96	0.4042
0.4063	17.0	102	0.3745
0.3781	18.0	108	0.3800
0.3919	19.0	114	0.3520
0.3600	20.0	120	0.3237
0.3449	21.0	126	0.2963
0.3199	22.0	132	0.3008
0.3220	23.0	138	0.2882
0.3037	24.0	144	0.2534
0.2746	25.0	150	0.2573
0.2700	26.0	156	0.2359
0.2573	27.0	162	0.2204
0.2392	28.0	168	0.2122
0.2339	29.0	174	0.2000
0.2208	30.0	180	0.1913
0.2159	31.0	186	0.1816
0.1982	32.0	192	0.1747
0.1967	33.0	198	0.1665
0.1868	34.0	204	0.1642
0.1804	35.0	210	0.1589
0.1797	36.0	216	0.1555
0.1731	37.0	222	0.1524
0.1698	38.0	228	0.1471
0.1679	39.0	234	0.1440
0.1667	40.0	240	0.1433

Framework versions

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