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: 0.4101

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
1.9065	1.0	5	1.4456
1.4155	2.0	10	1.2758
1.2760	3.0	15	1.1750
1.1812	4.0	20	1.1125
1.1029	5.0	25	1.0135
1.0238	6.0	30	0.9452
0.9754	7.0	35	1.0039
1.0038	8.0	40	0.8954
0.9197	9.0	45	0.8593
0.9007	10.0	50	0.8470
0.8615	11.0	55	0.8050
0.8225	12.0	60	0.7646
0.7921	13.0	65	0.7265
0.7955	14.0	70	0.7123
0.7526	15.0	75	0.6853
0.7354	16.0	80	0.6793
0.7253	17.0	85	0.6548
0.7005	18.0	90	0.6337
0.6761	19.0	95	0.6158
0.6566	20.0	100	0.5916
0.6642	21.0	105	0.5759
0.6408	22.0	110	0.5735
0.6353	23.0	115	0.5868
0.6286	24.0	120	0.5503
0.6109	25.0	125	0.5538
0.6068	26.0	130	0.5321
0.5774	27.0	135	0.5221
0.5733	28.0	140	0.5113
0.5716	29.0	145	0.5014
0.5593	30.0	150	0.4884
0.5554	31.0	155	0.4771
0.5422	32.0	160	0.4739
0.5319	33.0	165	0.4565
0.5182	34.0	170	0.4458
0.5100	35.0	175	0.4406
0.5040	36.0	180	0.4282
0.4940	37.0	185	0.4242
0.4867	38.0	190	0.4195
0.4910	39.0	195	0.4116
0.4794	40.0	200	0.4101

Framework versions

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