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: 0.2167

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
2.9708	1.0	6	2.2532
2.0334	2.0	12	1.7317
1.5636	3.0	18	1.3306
1.2228	4.0	24	1.1101
1.0587	5.0	30	0.9678
0.9399	6.0	36	0.8654
0.8269	7.0	42	0.7420
0.7354	8.0	48	0.6981
0.6841	9.0	54	0.6609
0.6499	10.0	60	0.6128
0.592	11.0	66	0.5730
0.5651	12.0	72	0.5324
0.53	13.0	78	0.5232
0.5087	14.0	84	0.5066
0.5052	15.0	90	0.4966
0.4933	16.0	96	0.4476
0.4622	17.0	102	0.4559
0.4604	18.0	108	0.4520
0.4386	19.0	114	0.4525
0.4453	20.0	120	0.4345
0.4293	21.0	126	0.3955
0.3904	22.0	132	0.3695
0.3793	23.0	138	0.3614
0.3648	24.0	144	0.3463
0.3471	25.0	150	0.3247
0.3391	26.0	156	0.3100
0.3084	27.0	162	0.2981
0.3188	28.0	168	0.2901
0.3074	29.0	174	0.2791
0.2847	30.0	180	0.2832
0.2832	31.0	186	0.2637
0.2762	32.0	192	0.2596
0.2928	33.0	198	0.2487
0.2759	34.0	204	0.2408
0.2634	35.0	210	0.2334
0.2585	36.0	216	0.2270
0.2444	37.0	222	0.2227
0.2394	38.0	228	0.2183
0.2376	39.0	234	0.2174
0.2394	40.0	240	0.2167

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2