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: 0.2387

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
3.0501	1.0	6	2.2966
2.0486	2.0	12	1.7533
1.5929	3.0	18	1.3909
1.2724	4.0	24	1.1387
1.0906	5.0	30	0.9902
0.9501	6.0	36	0.8982
0.8489	7.0	42	0.8078
0.7684	8.0	48	0.7145
0.6872	9.0	54	0.6570
0.6574	10.0	60	0.6683
0.6364	11.0	66	0.6542
0.6217	12.0	72	0.5741
0.561	13.0	78	0.5594
0.548	14.0	84	0.5491
0.5447	15.0	90	0.5075
0.5114	16.0	96	0.5275
0.4897	17.0	102	0.4606
0.4736	18.0	108	0.4505
0.4536	19.0	114	0.4420
0.4438	20.0	120	0.4338
0.4178	21.0	126	0.4388
0.439	22.0	132	0.4336
0.4315	23.0	138	0.3953
0.4006	24.0	144	0.3763
0.3923	25.0	150	0.3776
0.3785	26.0	156	0.3616
0.38	27.0	162	0.3504
0.3546	28.0	168	0.3411
0.3507	29.0	174	0.3395
0.3518	30.0	180	0.3256
0.3324	31.0	186	0.3084
0.3161	32.0	192	0.2991
0.3043	33.0	198	0.2820
0.2977	34.0	204	0.2706
0.2911	35.0	210	0.2644
0.2843	36.0	216	0.2583
0.2662	37.0	222	0.2491
0.2737	38.0	228	0.2438
0.2599	39.0	234	0.2397
0.2647	40.0	240	0.2387

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.1+cu128
• Datasets 4.5.0
• Tokenizers 0.22.1