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
2.6369	1.0	6	2.0477
1.7565	2.0	12	1.3737
1.1734	3.0	18	0.9502
0.8518	4.0	24	0.7393
0.6819	5.0	30	0.5983
0.5682	6.0	36	0.5471
0.5061	7.0	42	0.4669
0.4481	8.0	48	0.4075
0.3943	9.0	54	0.3609
0.3549	10.0	60	0.3064
0.3008	11.0	66	0.2429
0.273	12.0	72	0.2077
0.2174	13.0	78	0.1596
0.1708	14.0	84	0.1402
0.1405	15.0	90	0.0785
0.1068	16.0	96	0.0725
0.1017	17.0	102	0.0490
0.0684	18.0	108	0.0417
0.0565	19.0	114	0.0290
0.0487	20.0	120	0.0237
0.0403	21.0	126	0.0164
0.0323	22.0	132	0.0141
0.0277	23.0	138	0.0126
0.0234	24.0	144	0.0088
0.0219	25.0	150	0.0076
0.0215	26.0	156	0.0088
0.0175	27.0	162	0.0072
0.0152	28.0	168	0.0057
0.0198	29.0	174	0.0057
0.0146	30.0	180	0.0055
0.0126	31.0	186	0.0055
0.0125	32.0	192	0.0045
0.0108	33.0	198	0.0041
0.0091	34.0	204	0.0042
0.0076	35.0	210	0.0038
0.0076	36.0	216	0.0036
0.0072	37.0	222	0.0035
0.0067	38.0	228	0.0035
0.0066	39.0	234	0.0034
0.0065	40.0	240	0.0034

Framework versions

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