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: 0.1171

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
3.0616	1.0	6	2.4103
2.1327	2.0	12	1.8156
1.6546	3.0	18	1.4538
1.3238	4.0	24	1.1793
1.0938	5.0	30	1.0270
0.9418	6.0	36	0.8882
0.8472	7.0	42	0.8048
0.8069	8.0	48	0.7782
0.7235	9.0	54	0.6833
0.6806	10.0	60	0.6410
0.626	11.0	66	0.5912
0.5771	12.0	72	0.5144
0.5162	13.0	78	0.4871
0.4921	14.0	84	0.4862
0.4791	15.0	90	0.4469
0.4594	16.0	96	0.3999
0.3923	17.0	102	0.3790
0.3812	18.0	108	0.3455
0.3584	19.0	114	0.3355
0.3303	20.0	120	0.2909
0.2955	21.0	126	0.2728
0.2934	22.0	132	0.3018
0.2927	23.0	138	0.2477
0.2647	24.0	144	0.2527
0.2712	25.0	150	0.2479
0.2469	26.0	156	0.2299
0.2568	27.0	162	0.2180
0.2518	28.0	168	0.2178
0.2378	29.0	174	0.2158
0.222	30.0	180	0.1843
0.1971	31.0	186	0.1780
0.1936	32.0	192	0.1677
0.1928	33.0	198	0.1573
0.1708	34.0	204	0.1471
0.153	35.0	210	0.1375
0.16	36.0	216	0.1321
0.1493	37.0	222	0.1255
0.1438	38.0	228	0.1204
0.1401	39.0	234	0.1181
0.1492	40.0	240	0.1171

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.20.3