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: 0.0710

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
3.0915	1.0	5	2.3521
2.1484	2.0	10	1.8601
1.7128	3.0	15	1.4527
1.3553	4.0	20	1.1778
1.1163	5.0	25	1.0277
0.9841	6.0	30	0.9234
0.8693	7.0	35	0.7778
0.7649	8.0	40	0.7049
0.7043	9.0	45	0.6547
0.6440	10.0	50	0.6092
0.6069	11.0	55	0.5777
0.5713	12.0	60	0.5318
0.5384	13.0	65	0.4881
0.5031	14.0	70	0.4651
0.4705	15.0	75	0.4390
0.4453	16.0	80	0.4080
0.4165	17.0	85	0.3966
0.3953	18.0	90	0.3614
0.3782	19.0	95	0.3430
0.3625	20.0	100	0.3272
0.3394	21.0	105	0.3016
0.3107	22.0	110	0.2624
0.2814	23.0	115	0.2426
0.2610	24.0	120	0.2223
0.2468	25.0	125	0.1960
0.2233	26.0	130	0.1802
0.2052	27.0	135	0.1603
0.1890	28.0	140	0.1367
0.1708	29.0	145	0.1219
0.1577	30.0	150	0.1105
0.1487	31.0	155	0.1030
0.1400	32.0	160	0.0960
0.1308	33.0	165	0.0913
0.1265	34.0	170	0.0849
0.1187	35.0	175	0.0796
0.1138	36.0	180	0.0781
0.1113	37.0	185	0.0747
0.1079	38.0	190	0.0743
0.1083	39.0	195	0.0714
0.1057	40.0	200	0.0710

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2