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: 0.2454

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
2.9842	1.0	6	2.2874
2.0465	2.0	12	1.7769
1.5772	3.0	18	1.3812
1.3006	4.0	24	1.1717
1.0791	5.0	30	0.9973
0.9229	6.0	36	0.9593
0.8693	7.0	42	0.8263
0.7761	8.0	48	0.7712
0.7538	9.0	54	0.7099
0.6978	10.0	60	0.6758
0.6444	11.0	66	0.6319
0.6149	12.0	72	0.6014
0.5944	13.0	78	0.6130
0.5737	14.0	84	0.6018
0.5763	15.0	90	0.5680
0.5335	16.0	96	0.5525
0.5281	17.0	102	0.5220
0.4979	18.0	108	0.4794
0.4668	19.0	114	0.4779
0.4612	20.0	120	0.4558
0.4527	21.0	126	0.4302
0.4214	22.0	132	0.4414
0.4221	23.0	138	0.4328
0.4271	24.0	144	0.4047
0.4004	25.0	150	0.3844
0.3744	26.0	156	0.3687
0.3655	27.0	162	0.3484
0.3312	28.0	168	0.3504
0.3473	29.0	174	0.3289
0.3368	30.0	180	0.3246
0.3171	31.0	186	0.3189
0.3205	32.0	192	0.2958
0.3108	33.0	198	0.2881
0.2943	34.0	204	0.2756
0.2926	35.0	210	0.2699
0.2803	36.0	216	0.2594
0.2794	37.0	222	0.2539
0.2826	38.0	228	0.2501
0.272	39.0	234	0.2475
0.2576	40.0	240	0.2454

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2