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: 0.1653

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
3.0109	1.0	6	2.2927
2.0615	2.0	12	1.7747
1.6032	3.0	18	1.3800
1.2593	4.0	24	1.1547
1.0716	5.0	30	0.9624
0.9082	6.0	36	0.8484
0.8499	7.0	42	0.7745
0.7568	8.0	48	0.7185
0.697	9.0	54	0.6622
0.6241	10.0	60	0.6027
0.5987	11.0	66	0.6118
0.5967	12.0	72	0.5614
0.5571	13.0	78	0.5211
0.5126	14.0	84	0.4899
0.4919	15.0	90	0.4756
0.4617	16.0	96	0.4457
0.4471	17.0	102	0.4410
0.4298	18.0	108	0.4136
0.4146	19.0	114	0.4060
0.395	20.0	120	0.3893
0.3749	21.0	126	0.3975
0.3747	22.0	132	0.3598
0.3559	23.0	138	0.3660
0.3465	24.0	144	0.3253
0.3257	25.0	150	0.3112
0.3085	26.0	156	0.2785
0.292	27.0	162	0.2639
0.2807	28.0	168	0.2507
0.2689	29.0	174	0.2342
0.2526	30.0	180	0.2241
0.2424	31.0	186	0.2149
0.2293	32.0	192	0.2103
0.2175	33.0	198	0.1970
0.2189	34.0	204	0.1867
0.2092	35.0	210	0.1831
0.199	36.0	216	0.1837
0.2095	37.0	222	0.1739
0.1912	38.0	228	0.1707
0.188	39.0	234	0.1671
0.1855	40.0	240	0.1653

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2