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: 1.4131

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
3.3688	1.0	6	2.7446
2.3519	2.0	12	2.0185
1.8781	3.0	18	1.7058
1.6266	4.0	24	1.6304
1.614	5.0	30	1.5637
1.6233	6.0	36	1.5529
1.5566	7.0	42	1.5884
1.5389	8.0	48	1.5444
1.5121	9.0	54	1.5489
1.5376	10.0	60	1.5411
1.532	11.0	66	1.5396
1.5576	12.0	72	1.5405
1.5914	13.0	78	1.5442
1.5226	14.0	84	1.5356
1.5129	15.0	90	1.5327
1.5037	16.0	96	1.5333
1.5191	17.0	102	1.5379
1.4822	18.0	108	1.5329
1.5205	19.0	114	1.5272
1.6166	20.0	120	1.5257
1.5019	21.0	126	1.5286
1.5512	22.0	132	1.5284
1.5532	23.0	138	1.5302
1.5016	24.0	144	1.5287
1.4958	25.0	150	1.5302
1.4917	26.0	156	1.5260
1.5	27.0	162	1.5249
1.5572	28.0	168	1.5272
1.5552	29.0	174	1.5259
1.545	30.0	180	1.5121
1.519	31.0	186	1.5229
1.5074	32.0	192	1.5117
1.4766	33.0	198	1.4902
1.4597	34.0	204	1.4815
1.4488	35.0	210	1.4592
1.4401	36.0	216	1.4433
1.4376	37.0	222	1.4322
1.3936	38.0	228	1.4231
1.4553	39.0	234	1.4220
1.4191	40.0	240	1.4131

Framework versions

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