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: 0.0034

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
0.774	1.0	6	0.6889
0.6421	2.0	12	0.5684
0.5589	3.0	18	0.5287
0.5027	4.0	24	0.4892
0.4758	5.0	30	0.4412
0.4368	6.0	36	0.3770
0.3433	7.0	42	0.3218
0.2925	8.0	48	0.2518
0.2501	9.0	54	0.2048
0.2011	10.0	60	0.1582
0.1645	11.0	66	0.1267
0.1205	12.0	72	0.1078
0.1064	13.0	78	0.1005
0.0961	14.0	84	0.0677
0.0953	15.0	90	0.0549
0.069	16.0	96	0.0480
0.0593	17.0	102	0.0371
0.0516	18.0	108	0.0292
0.0436	19.0	114	0.0242
0.0381	20.0	120	0.0252
0.035	21.0	126	0.0157
0.0341	22.0	132	0.0135
0.0361	23.0	138	0.0140
0.0292	24.0	144	0.0117
0.0245	25.0	150	0.0131
0.0223	26.0	156	0.0082
0.0216	27.0	162	0.0093
0.0156	28.0	168	0.0073
0.0135	29.0	174	0.0054
0.0113	30.0	180	0.0052
0.0108	31.0	186	0.0045
0.0084	32.0	192	0.0042
0.0084	33.0	198	0.0039
0.0074	34.0	204	0.0037
0.007	35.0	210	0.0036
0.0067	36.0	216	0.0036
0.0065	37.0	222	0.0035
0.0066	38.0	228	0.0034
0.0066	39.0	234	0.0034
0.0064	40.0	240	0.0034

Framework versions

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