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: 0.6006

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
3.486	1.0	5	2.9161
2.5763	2.0	10	2.1493
1.965	3.0	15	1.7717
1.6868	4.0	20	1.6013
1.5787	5.0	25	1.5372
1.5007	6.0	30	1.4588
1.428	7.0	35	1.4072
1.4041	8.0	40	1.3590
1.3104	9.0	45	1.2594
1.279	10.0	50	1.2948
1.2457	11.0	55	1.2035
1.1598	12.0	60	1.0922
1.0812	13.0	65	1.0745
1.0613	14.0	70	1.0448
1.0542	15.0	75	1.0009
1.0459	16.0	80	0.9843
1.0733	17.0	85	1.1919
1.0664	18.0	90	1.0079
0.9639	19.0	95	0.9124
0.9094	20.0	100	0.8717
0.8693	21.0	105	0.8281
0.8348	22.0	110	0.7971
0.8095	23.0	115	0.8027
0.7985	24.0	120	0.7565
0.784	25.0	125	0.7354
0.7934	26.0	130	0.8105
0.7754	27.0	135	0.7499
0.7381	28.0	140	0.6967
0.7124	29.0	145	0.6911
0.7058	30.0	150	0.6855
0.6998	31.0	155	0.6779
0.6966	32.0	160	0.6676
0.6859	33.0	165	0.6618
0.6774	34.0	170	0.6418
0.6617	35.0	175	0.6278
0.6521	36.0	180	0.6152
0.6422	37.0	185	0.6121
0.6358	38.0	190	0.6074
0.631	39.0	195	0.6022
0.6294	40.0	200	0.6006

Framework versions

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