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: 0.6587

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
3.3715	1.0	6	2.7668
2.4459	2.0	12	2.0165
1.8589	3.0	18	1.7392
1.7744	4.0	24	1.6714
1.6018	5.0	30	1.5897
1.4921	6.0	36	1.5386
1.4816	7.0	42	1.4612
1.4355	8.0	48	1.4503
1.33	9.0	54	1.3248
1.2827	10.0	60	1.2280
1.234	11.0	66	1.2248
1.2229	12.0	72	1.3745
1.2522	13.0	78	1.1725
1.1299	14.0	84	1.0781
1.0669	15.0	90	1.0417
1.0125	16.0	96	1.0053
0.9977	17.0	102	1.0263
1.0611	18.0	108	1.0528
1.0357	19.0	114	0.9557
0.927	20.0	120	0.9334
0.9075	21.0	126	0.8948
0.8795	22.0	132	0.9888
0.9473	23.0	138	0.9332
0.8718	24.0	144	0.8529
0.8661	25.0	150	0.8421
0.8381	26.0	156	0.8280
0.7939	27.0	162	0.7921
0.8426	28.0	168	0.7751
0.7897	29.0	174	0.7592
0.7687	30.0	180	0.7575
0.77	31.0	186	0.7346
0.7479	32.0	192	0.7266
0.7247	33.0	198	0.7156
0.7278	34.0	204	0.7154
0.7241	35.0	210	0.6853
0.7037	36.0	216	0.6897
0.6949	37.0	222	0.6697
0.7135	38.0	228	0.6661
0.6864	39.0	234	0.6619
0.6812	40.0	240	0.6587

Framework versions

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