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: 0.1069

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: 0.0003
• 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: 70
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.1895	1.0	6	2.6427
2.5023	2.0	12	2.3194
2.2164	3.0	18	2.0818
1.9817	4.0	24	1.8459
1.7401	5.0	30	1.5845
1.4949	6.0	36	1.3665
1.3165	7.0	42	1.2362
1.1900	8.0	48	1.1268
1.0863	9.0	54	1.0420
1.0146	10.0	60	0.9612
0.9334	11.0	66	0.8996
0.8609	12.0	72	0.8165
0.7963	13.0	78	0.7590
0.7421	14.0	84	0.7111
0.7035	15.0	90	0.6801
0.6712	16.0	96	0.6426
0.6280	17.0	102	0.6165
0.6134	18.0	108	0.6010
0.5910	19.0	114	0.5739
0.5714	20.0	120	0.5586
0.5493	21.0	126	0.5467
0.5482	22.0	132	0.5332
0.5189	23.0	138	0.5065
0.5028	24.0	144	0.4866
0.4837	25.0	150	0.4671
0.4711	26.0	156	0.4461
0.4482	27.0	162	0.4298
0.4262	28.0	168	0.4064
0.4098	29.0	174	0.3933
0.3945	30.0	180	0.3733
0.3810	31.0	186	0.3547
0.3614	32.0	192	0.3353
0.3432	33.0	198	0.3179
0.3322	34.0	204	0.3003
0.3181	35.0	210	0.2997
0.3149	36.0	216	0.2767
0.2864	37.0	222	0.2600
0.2819	38.0	228	0.2418
0.2663	39.0	234	0.2296
0.2591	40.0	240	0.2176
0.2535	41.0	246	0.2106
0.2314	42.0	252	0.1970
0.2277	43.0	258	0.1849
0.2231	44.0	264	0.1754
0.2109	45.0	270	0.1750
0.1956	46.0	276	0.1640
0.1933	47.0	282	0.1597
0.1826	48.0	288	0.1556
0.1831	49.0	294	0.1550
0.1776	50.0	300	0.1436
0.1671	51.0	306	0.1417
0.1773	52.0	312	0.1349
0.1617	53.0	318	0.1311
0.1600	54.0	324	0.1333
0.1557	55.0	330	0.1274
0.1548	56.0	336	0.1231
0.1486	57.0	342	0.1217
0.1484	58.0	348	0.1201
0.1434	59.0	354	0.1169
0.1375	60.0	360	0.1179
0.1418	61.0	366	0.1142
0.1377	62.0	372	0.1119
0.1422	63.0	378	0.1115
0.1315	64.0	384	0.1104
0.1362	65.0	390	0.1106
0.1380	66.0	396	0.1084
0.1326	67.0	402	0.1072
0.1311	68.0	408	0.1078
0.1396	69.0	414	0.1073
0.1340	70.0	420	0.1069

Framework versions

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