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: 0.2172

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
3.0547	1.0	6	2.3235
2.0645	2.0	12	1.8699
1.6975	3.0	18	1.5582
1.4058	4.0	24	1.2875
1.1930	5.0	30	1.0846
1.0571	6.0	36	1.0523
0.9713	7.0	42	0.9177
0.8768	8.0	48	0.9016
0.8688	9.0	54	0.8003
0.7712	10.0	60	0.7546
0.7255	11.0	66	0.6924
0.6674	12.0	72	0.6362
0.6104	13.0	78	0.6404
0.5723	14.0	84	0.5483
0.5251	15.0	90	0.5152
0.5100	16.0	96	0.4806
0.4442	17.0	102	0.4510
0.4643	18.0	108	0.4321
0.4391	19.0	114	0.4565
0.4395	20.0	120	0.4186
0.4202	21.0	126	0.3869
0.4038	22.0	132	0.3577
0.3632	23.0	138	0.3645
0.3682	24.0	144	0.3557
0.3688	25.0	150	0.3535
0.3548	26.0	156	0.3524
0.3401	27.0	162	0.3203
0.3440	28.0	168	0.3018
0.3059	29.0	174	0.2777
0.2963	30.0	180	0.2761
0.2960	31.0	186	0.2661
0.2681	32.0	192	0.2570
0.2578	33.0	198	0.2479
0.2549	34.0	204	0.2413
0.2702	35.0	210	0.2329
0.2488	36.0	216	0.2267
0.2550	37.0	222	0.2219
0.2324	38.0	228	0.2206
0.2294	39.0	234	0.2190
0.2242	40.0	240	0.2172

Framework versions

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