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: 0.9541

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: 0.0001
• 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
3.6580	1.0	6	3.2453
3.1079	2.0	12	2.8981
2.8039	3.0	18	2.6629
2.6131	4.0	24	2.5056
2.4617	5.0	30	2.3752
2.3350	6.0	36	2.2642
2.2296	7.0	42	2.1748
2.1459	8.0	48	2.0943
2.0633	9.0	54	2.0142
1.9671	10.0	60	1.9194
1.8781	11.0	66	1.8104
1.7735	12.0	72	1.6989
1.6788	13.0	78	1.6040
1.5891	14.0	84	1.5262
1.5152	15.0	90	1.4682
1.4592	16.0	96	1.4185
1.4132	17.0	102	1.3766
1.3728	18.0	108	1.3385
1.3356	19.0	114	1.3063
1.3025	20.0	120	1.2722
1.2656	21.0	126	1.2434
1.2433	22.0	132	1.2168
1.2150	23.0	138	1.1880
1.1891	24.0	144	1.1642
1.1656	25.0	150	1.1414
1.1386	26.0	156	1.1177
1.1159	27.0	162	1.0988
1.0934	28.0	168	1.0751
1.0739	29.0	174	1.0548
1.0619	30.0	180	1.0354
1.0372	31.0	186	1.0206
1.0235	32.0	192	1.0072
1.0175	33.0	198	0.9949
1.0034	34.0	204	0.9841
0.9859	35.0	210	0.9759
0.9895	36.0	216	0.9683
0.9779	37.0	222	0.9622
0.9706	38.0	228	0.9574
0.9735	39.0	234	0.9549
0.9607	40.0	240	0.9541

Framework versions

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