calculator_model_test2

This model is a fine-tuned version of LordAbsurd2137/calculator_model_test2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0222

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
1.0953	1.0	6	0.6430
0.5025	2.0	12	0.4289
0.3633	3.0	18	0.3352
0.3426	4.0	24	0.2911
0.284	5.0	30	0.2464
0.2408	6.0	36	0.1998
0.2168	7.0	42	0.1874
0.1815	8.0	48	0.1592
0.1684	9.0	54	0.1547
0.1604	10.0	60	0.1707
0.1603	11.0	66	0.1516
0.1498	12.0	72	0.1220
0.1307	13.0	78	0.1079
0.1154	14.0	84	0.1270
0.1157	15.0	90	0.0997
0.1038	16.0	96	0.0919
0.1005	17.0	102	0.1005
0.097	18.0	108	0.1103
0.1019	19.0	114	0.1285
0.1067	20.0	120	0.1202
0.0995	21.0	126	0.0810
0.0799	22.0	132	0.0774
0.0723	23.0	138	0.0678
0.0656	24.0	144	0.0655
0.0666	25.0	150	0.0637
0.0606	26.0	156	0.0541
0.0562	27.0	162	0.0497
0.0524	28.0	168	0.0519
0.0556	29.0	174	0.0616
0.0584	30.0	180	0.0448
0.0496	31.0	186	0.0451
0.0484	32.0	192	0.0413
0.0454	33.0	198	0.0444
0.0411	34.0	204	0.0423
0.0395	35.0	210	0.0376
0.0383	36.0	216	0.0358
0.0373	37.0	222	0.0326
0.035	38.0	228	0.0286
0.0323	39.0	234	0.0307
0.0306	40.0	240	0.0279
0.029	41.0	246	0.0265
0.0296	42.0	252	0.0259
0.0263	43.0	258	0.0259
0.0244	44.0	264	0.0232
0.0264	45.0	270	0.0234
0.0263	46.0	276	0.0226
0.0223	47.0	282	0.0227
0.0225	48.0	288	0.0224
0.0218	49.0	294	0.0222
0.0216	50.0	300	0.0222

Framework versions

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