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: 0.2737

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
1.3165	1.0	6	0.6014
0.5027	2.0	12	0.3749
0.3429	3.0	18	0.3721
0.3684	4.0	24	0.3056
0.3082	5.0	30	0.2904
0.2893	6.0	36	0.2771
0.2804	7.0	42	0.3063
0.2879	8.0	48	0.2761
0.2749	9.0	54	0.2786
0.2709	10.0	60	0.2812
0.2775	11.0	66	0.2772
0.2723	12.0	72	0.2790
0.2699	13.0	78	0.2743
0.2642	14.0	84	0.2763
0.2704	15.0	90	0.2740
0.2698	16.0	96	0.2747
0.2695	17.0	102	0.2741
0.2759	18.0	108	0.2738
0.2682	19.0	114	0.2756
0.2700	20.0	120	0.2749
0.2663	21.0	126	0.2737
0.2692	22.0	132	0.2750
0.2682	23.0	138	0.2738
0.2686	24.0	144	0.2752
0.2711	25.0	150	0.2734
0.2673	26.0	156	0.2743
0.2625	27.0	162	0.2761
0.2760	28.0	168	0.2734
0.2738	29.0	174	0.2738
0.2609	30.0	180	0.2754
0.2699	31.0	186	0.2758
0.2677	32.0	192	0.2733
0.2728	33.0	198	0.2735
0.2709	34.0	204	0.2734
0.2727	35.0	210	0.2733
0.2726	36.0	216	0.2733
0.2706	37.0	222	0.2733
0.2668	38.0	228	0.2734
0.2728	39.0	234	0.2737
0.2684	40.0	240	0.2737

Framework versions

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