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: 0.0095

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
2.4753	1.0	13	1.7336
1.3843	2.0	26	0.9380
0.8281	3.0	39	0.7141
0.6509	4.0	52	0.5507
0.5643	5.0	65	0.5065
0.5155	6.0	78	0.4642
0.445	7.0	91	0.3848
0.3912	8.0	104	0.3584
0.3564	9.0	117	0.3142
0.3175	10.0	130	0.2663
0.2765	11.0	143	0.2291
0.2436	12.0	156	0.1915
0.2186	13.0	169	0.1556
0.1646	14.0	182	0.1097
0.1504	15.0	195	0.0862
0.113	16.0	208	0.0725
0.0864	17.0	221	0.0500
0.0722	18.0	234	0.0425
0.0654	19.0	247	0.0389
0.0581	20.0	260	0.0312
0.052	21.0	273	0.0284
0.0459	22.0	286	0.0275
0.0426	23.0	299	0.0213
0.0381	24.0	312	0.0200
0.0374	25.0	325	0.0186
0.0334	26.0	338	0.0185
0.0307	27.0	351	0.0157
0.0292	28.0	364	0.0147
0.0269	29.0	377	0.0146
0.0261	30.0	390	0.0129
0.0248	31.0	403	0.0121
0.0237	32.0	416	0.0114
0.023	33.0	429	0.0115
0.0217	34.0	442	0.0109
0.0208	35.0	455	0.0101
0.0205	36.0	468	0.0102
0.0197	37.0	481	0.0098
0.0193	38.0	494	0.0096
0.019	39.0	507	0.0094
0.0188	40.0	520	0.0095

Framework versions

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