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: 0.5655

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
3.4577	1.0	5	2.8856
2.5445	2.0	10	2.1155
1.9433	3.0	15	1.7402
1.6716	4.0	20	1.5984
1.5706	5.0	25	1.5216
1.4716	6.0	30	1.4133
1.4078	7.0	35	1.4063
1.3399	8.0	40	1.2725
1.2563	9.0	45	1.1975
1.1916	10.0	50	1.1727
1.1233	11.0	55	1.0583
1.0715	12.0	60	1.0389
1.0457	13.0	65	1.0173
1.0079	14.0	70	0.9519
0.9752	15.0	75	0.9463
0.9617	16.0	80	0.9936
0.9496	17.0	85	0.8543
0.8664	18.0	90	0.8184
0.8374	19.0	95	0.8107
0.8280	20.0	100	0.8515
0.8739	21.0	105	0.8150
0.8371	22.0	110	0.7676
0.7851	23.0	115	0.7262
0.7736	24.0	120	0.7195
0.7422	25.0	125	0.7092
0.7317	26.0	130	0.6800
0.7113	27.0	135	0.6642
0.6888	28.0	140	0.6617
0.6923	29.0	145	0.6446
0.6785	30.0	150	0.6787
0.6754	31.0	155	0.6197
0.6616	32.0	160	0.6091
0.6520	33.0	165	0.6110
0.6432	34.0	170	0.5926
0.6334	35.0	175	0.5935
0.6235	36.0	180	0.5870
0.6212	37.0	185	0.5840
0.6134	38.0	190	0.5712
0.6072	39.0	195	0.5662
0.6043	40.0	200	0.5655

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cpu
• Datasets 4.0.0
• Tokenizers 0.22.2