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: 0.5921

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
3.462	1.0	5	2.8547
2.538	2.0	10	2.0897
1.9404	3.0	15	1.7253
1.7165	4.0	20	1.6144
1.6205	5.0	25	1.5616
1.5595	6.0	30	1.5343
1.533	7.0	35	1.5129
1.5116	8.0	40	1.4738
1.47	9.0	45	1.4300
1.4339	10.0	50	1.4170
1.4026	11.0	55	1.3703
1.3849	12.0	60	1.3283
1.3616	13.0	65	1.2966
1.3063	14.0	70	1.2537
1.2479	15.0	75	1.1862
1.1756	16.0	80	1.1101
1.1533	17.0	85	1.1242
1.1344	18.0	90	1.1090
1.0864	19.0	95	1.0031
1.0175	20.0	100	0.9584
0.9662	21.0	105	0.9226
0.9294	22.0	110	0.8753
0.8923	23.0	115	0.8596
0.8676	24.0	120	0.8074
0.8371	25.0	125	0.7753
0.8185	26.0	130	0.7829
0.8092	27.0	135	0.7452
0.7693	28.0	140	0.7231
0.7534	29.0	145	0.7025
0.7432	30.0	150	0.6977
0.7249	31.0	155	0.6820
0.7161	32.0	160	0.6609
0.703	33.0	165	0.6529
0.6926	34.0	170	0.6395
0.6771	35.0	175	0.6246
0.667	36.0	180	0.6204
0.6633	37.0	185	0.6057
0.6498	38.0	190	0.6014
0.642	39.0	195	0.5947
0.6433	40.0	200	0.5921

Framework versions

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