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: 2.4280

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
2.9289	1.0	6	2.2631
2.0248	2.0	12	1.8559
1.6028	3.0	18	1.7034
1.2773	4.0	24	1.6626
1.0862	5.0	30	1.6454
0.9687	6.0	36	1.8670
0.8858	7.0	42	1.8190
0.7782	8.0	48	2.0888
0.7379	9.0	54	2.1530
0.7093	10.0	60	2.1941
0.6654	11.0	66	2.0807
0.6296	12.0	72	2.1993
0.5963	13.0	78	2.2719
0.5661	14.0	84	2.2821
0.5392	15.0	90	2.2940
0.5209	16.0	96	2.3435
0.4862	17.0	102	2.3659
0.4886	18.0	108	2.4129
0.4668	19.0	114	2.5027
0.4577	20.0	120	2.5144
0.4426	21.0	126	2.4393
0.4198	22.0	132	2.4533
0.4200	23.0	138	2.4996
0.3980	24.0	144	2.4961
0.3715	25.0	150	2.4773
0.3642	26.0	156	2.4326
0.3530	27.0	162	2.4626
0.3300	28.0	168	2.4540
0.3190	29.0	174	2.4593
0.3125	30.0	180	2.4535
0.3008	31.0	186	2.4917
0.2989	32.0	192	2.4753
0.2802	33.0	198	2.4765
0.2677	34.0	204	2.4505
0.2569	35.0	210	2.4462
0.2535	36.0	216	2.4243
0.2586	37.0	222	2.4185
0.2421	38.0	228	2.4217
0.2463	39.0	234	2.4261
0.2430	40.0	240	2.4280

Framework versions

• Transformers 5.2.0
• Pytorch 2.10.0
• Datasets 4.6.1
• Tokenizers 0.22.2