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: 0.0824

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
2.9085	1.0	6	2.2339
1.9955	2.0	12	1.7507
1.5891	3.0	18	1.3630
1.221	4.0	24	1.0757
1.0321	5.0	30	0.9606
0.9056	6.0	36	0.8336
0.8119	7.0	42	0.7754
0.7251	8.0	48	0.7105
0.679	9.0	54	0.6689
0.6367	10.0	60	0.6193
0.5903	11.0	66	0.5498
0.5423	12.0	72	0.5078
0.5121	13.0	78	0.5079
0.4916	14.0	84	0.4614
0.4659	15.0	90	0.4271
0.4173	16.0	96	0.4071
0.3995	17.0	102	0.3885
0.3809	18.0	108	0.3586
0.3564	19.0	114	0.3231
0.3277	20.0	120	0.3317
0.3156	21.0	126	0.3146
0.3124	22.0	132	0.3063
0.2829	23.0	138	0.2604
0.2624	24.0	144	0.2385
0.2431	25.0	150	0.2421
0.23	26.0	156	0.1983
0.1995	27.0	162	0.1716
0.1857	28.0	168	0.1565
0.1654	29.0	174	0.1325
0.1477	30.0	180	0.1246
0.1489	31.0	186	0.1188
0.1352	32.0	192	0.1075
0.1232	33.0	198	0.1017
0.1205	34.0	204	0.0963
0.1125	35.0	210	0.0912
0.1149	36.0	216	0.0903
0.1081	37.0	222	0.0903
0.1069	38.0	228	0.0851
0.1046	39.0	234	0.0828
0.0996	40.0	240	0.0824

Framework versions

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