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: 0.2087

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
2.9918	1.0	6	2.3314
2.1182	2.0	12	1.8298
1.6911	3.0	18	1.4816
1.3856	4.0	24	1.2456
1.1721	5.0	30	1.1107
1.0415	6.0	36	0.9727
0.9122	7.0	42	0.8805
0.8414	8.0	48	0.7747
0.7661	9.0	54	0.7645
0.7303	10.0	60	0.6846
0.683	11.0	66	0.6398
0.6329	12.0	72	0.6278
0.6155	13.0	78	0.5686
0.6154	14.0	84	0.5761
0.5568	15.0	90	0.5522
0.5444	16.0	96	0.5564
0.56	17.0	102	0.5432
0.5165	18.0	108	0.4867
0.4824	19.0	114	0.4501
0.4487	20.0	120	0.4368
0.4322	21.0	126	0.4188
0.4173	22.0	132	0.4008
0.3965	23.0	138	0.3789
0.3953	24.0	144	0.3752
0.3627	25.0	150	0.3527
0.3766	26.0	156	0.3516
0.3505	27.0	162	0.3362
0.3441	28.0	168	0.3086
0.3264	29.0	174	0.3030
0.3395	30.0	180	0.2783
0.2908	31.0	186	0.2727
0.2827	32.0	192	0.2742
0.2857	33.0	198	0.2503
0.2779	34.0	204	0.2421
0.2543	35.0	210	0.2257
0.2462	36.0	216	0.2232
0.2421	37.0	222	0.2173
0.2497	38.0	228	0.2130
0.2561	39.0	234	0.2095
0.2407	40.0	240	0.2087

Framework versions

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