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: 0.6494

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
3.41	1.0	6	2.7285
2.3554	2.0	12	1.9345
1.7997	3.0	18	1.7097
1.6321	4.0	24	1.5813
1.5569	5.0	30	1.5555
1.5351	6.0	36	1.5315
1.5153	7.0	42	1.4900
1.4628	8.0	48	1.4687
1.4525	9.0	54	1.4173
1.4163	10.0	60	1.4669
1.4614	11.0	66	1.4160
1.4123	12.0	72	1.5650
1.4659	13.0	78	1.3993
1.3836	14.0	84	1.3573
1.3294	15.0	90	1.2931
1.2608	16.0	96	1.2117
1.1995	17.0	102	1.1448
1.128	18.0	108	1.0709
1.0898	19.0	114	1.0349
1.0419	20.0	120	0.9931
1.0328	21.0	126	0.9382
0.977	22.0	132	0.9141
0.9489	23.0	138	0.8951
0.909	24.0	144	0.8683
0.8942	25.0	150	0.8752
0.879	26.0	156	0.8352
0.8636	27.0	162	0.7924
0.836	28.0	168	0.7670
0.8144	29.0	174	0.7784
0.7994	30.0	180	0.7718
0.8059	31.0	186	0.7409
0.8033	32.0	192	0.7347
0.7942	33.0	198	0.7163
0.7723	34.0	204	0.6903
0.7396	35.0	210	0.6846
0.7462	36.0	216	0.6722
0.7344	37.0	222	0.6712
0.728	38.0	228	0.6564
0.7185	39.0	234	0.6536
0.7316	40.0	240	0.6494

Framework versions

• Transformers 4.45.2
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.20.3