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: 0.0732

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
3.1329	1.0	5	2.4115
2.1734	2.0	10	1.8467
1.7271	3.0	15	1.5298
1.4359	4.0	20	1.2764
1.1968	5.0	25	1.0395
0.9850	6.0	30	0.8995
0.8588	7.0	35	0.7843
0.7775	8.0	40	0.7370
0.7156	9.0	45	0.6533
0.6477	10.0	50	0.5932
0.5889	11.0	55	0.5227
0.5340	12.0	60	0.4886
0.4974	13.0	65	0.4334
0.4522	14.0	70	0.3877
0.4190	15.0	75	0.3612
0.3872	16.0	80	0.3277
0.3550	17.0	85	0.2904
0.3289	18.0	90	0.2736
0.3074	19.0	95	0.2424
0.2834	20.0	100	0.2317
0.2678	21.0	105	0.2062
0.2496	22.0	110	0.2049
0.2352	23.0	115	0.1744
0.2159	24.0	120	0.1553
0.2043	25.0	125	0.1476
0.1886	26.0	130	0.1313
0.1749	27.0	135	0.1227
0.1676	28.0	140	0.1168
0.1610	29.0	145	0.1098
0.1508	30.0	150	0.1045
0.1424	31.0	155	0.0956
0.1354	32.0	160	0.0904
0.1315	33.0	165	0.0851
0.1257	34.0	170	0.0823
0.1228	35.0	175	0.0800
0.1173	36.0	180	0.0777
0.1132	37.0	185	0.0760
0.1131	38.0	190	0.0749
0.1136	39.0	195	0.0735
0.1115	40.0	200	0.0732

Framework versions

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