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: 0.6087

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
3.3748	1.0	6	2.7546
2.3666	2.0	12	2.0282
1.8315	3.0	18	1.6880
1.616	4.0	24	1.5382
1.503	5.0	30	1.4603
1.4344	6.0	36	1.4103
1.3878	7.0	42	1.3806
1.3418	8.0	48	1.2722
1.2509	9.0	54	1.2194
1.2581	10.0	60	1.2255
1.2361	11.0	66	1.4183
1.259	12.0	72	1.1575
1.1246	13.0	78	1.1058
1.0757	14.0	84	1.0496
1.0499	15.0	90	1.0402
0.9797	16.0	96	0.9715
0.9347	17.0	102	0.9876
0.9267	18.0	108	0.9119
0.8861	19.0	114	0.9250
0.9253	20.0	120	0.8471
0.9204	21.0	126	0.8488
0.8545	22.0	132	0.8404
0.8283	23.0	138	0.7885
0.7892	24.0	144	0.8518
0.804	25.0	150	0.9104
0.8278	26.0	156	0.7776
0.7759	27.0	162	0.7776
0.7388	28.0	168	0.7396
0.7323	29.0	174	0.7238
0.727	30.0	180	0.6978
0.7104	31.0	186	0.6916
0.6964	32.0	192	0.6704
0.6797	33.0	198	0.6547
0.661	34.0	204	0.6457
0.6567	35.0	210	0.6497
0.6494	36.0	216	0.6411
0.6526	37.0	222	0.6314
0.6379	38.0	228	0.6150
0.6224	39.0	234	0.6093
0.6231	40.0	240	0.6087

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.1+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2