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: 0.7222

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
3.4163	1.0	6	2.8253
2.463	2.0	12	2.0984
1.8832	3.0	18	1.7286
1.6613	4.0	24	1.6379
1.5863	5.0	30	1.5767
1.5021	6.0	36	1.5366
1.4813	7.0	42	1.5000
1.4805	8.0	48	1.4118
1.4184	9.0	54	1.4590
1.3594	10.0	60	1.3815
1.3154	11.0	66	1.3336
1.3036	12.0	72	1.3426
1.2467	13.0	78	1.2566
1.1995	14.0	84	1.1788
1.1292	15.0	90	1.1819
1.1157	16.0	96	1.1389
1.1397	17.0	102	1.0924
1.1128	18.0	108	1.0831
1.0476	19.0	114	1.0312
1.0193	20.0	120	0.9820
1.0701	21.0	126	0.9712
0.9618	22.0	132	0.9326
0.9227	23.0	138	0.9335
0.9399	24.0	144	0.9046
0.9318	25.0	150	0.8951
0.9068	26.0	156	0.8831
0.8687	27.0	162	0.8611
0.848	28.0	168	0.8884
0.8559	29.0	174	0.8844
0.8439	30.0	180	0.8729
0.8453	31.0	186	0.8323
0.8154	32.0	192	0.8130
0.788	33.0	198	0.8038
0.7912	34.0	204	0.7717
0.7823	35.0	210	0.7539
0.7658	36.0	216	0.7556
0.7617	37.0	222	0.7427
0.7396	38.0	228	0.7340
0.7621	39.0	234	0.7243
0.7324	40.0	240	0.7222

Framework versions

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