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: 0.0094

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
2.9219	1.0	6	2.2235
1.9996	2.0	12	1.6925
1.4545	3.0	18	1.1007
0.9701	4.0	24	0.8044
0.7563	5.0	30	0.6572
0.5984	6.0	36	0.6227
0.5377	7.0	42	0.4585
0.442	8.0	48	0.3971
0.375	9.0	54	0.3378
0.3181	10.0	60	0.2967
0.2961	11.0	66	0.2787
0.2671	12.0	72	0.2398
0.2469	13.0	78	0.2102
0.2154	14.0	84	0.2098
0.2032	15.0	90	0.1873
0.1822	16.0	96	0.1632
0.1658	17.0	102	0.1475
0.1575	18.0	108	0.1309
0.1424	19.0	114	0.1175
0.1256	20.0	120	0.0999
0.1027	21.0	126	0.0867
0.0968	22.0	132	0.0781
0.0772	23.0	138	0.0648
0.0703	24.0	144	0.0522
0.0591	25.0	150	0.0427
0.0531	26.0	156	0.0322
0.0465	27.0	162	0.0296
0.0486	28.0	168	0.0284
0.0392	29.0	174	0.0280
0.0333	30.0	180	0.0264
0.0327	31.0	186	0.0172
0.0274	32.0	192	0.0175
0.0251	33.0	198	0.0149
0.0236	34.0	204	0.0143
0.0211	35.0	210	0.0115
0.0197	36.0	216	0.0106
0.0182	37.0	222	0.0111
0.0164	38.0	228	0.0105
0.0172	39.0	234	0.0097
0.0162	40.0	240	0.0094

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.20.3