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: 0.0011

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
2.3492	1.0	11	1.8446
1.6854	2.0	22	1.3965
1.1935	3.0	33	0.8348
0.5028	4.0	44	0.3122
0.2788	5.0	55	0.2400
0.2212	6.0	66	0.1893
0.1813	7.0	77	0.1544
0.1515	8.0	88	0.1281
0.1206	9.0	99	0.0903
0.087	10.0	110	0.0571
0.058	11.0	121	0.0359
0.0378	12.0	132	0.0204
0.0249	13.0	143	0.0126
0.0169	14.0	154	0.0085
0.0123	15.0	165	0.0061
0.009	16.0	176	0.0047
0.0073	17.0	187	0.0037
0.006	18.0	198	0.0031
0.0049	19.0	209	0.0024
0.0043	20.0	220	0.0023
0.0037	21.0	231	0.0020
0.0033	22.0	242	0.0019
0.0032	23.0	253	0.0018
0.003	24.0	264	0.0016
0.0025	25.0	275	0.0015
0.0024	26.0	286	0.0014
0.0023	27.0	297	0.0014
0.0022	28.0	308	0.0014
0.0021	29.0	319	0.0013
0.002	30.0	330	0.0012
0.0019	31.0	341	0.0012
0.0018	32.0	352	0.0012
0.0018	33.0	363	0.0012
0.0017	34.0	374	0.0011
0.0018	35.0	385	0.0011
0.0018	36.0	396	0.0011
0.0017	37.0	407	0.0011
0.0016	38.0	418	0.0011
0.0016	39.0	429	0.0011
0.0015	40.0	440	0.0011

Framework versions

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