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: 0.1171

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.9048	1.0	12	2.1270
1.9316	2.0	24	1.6532
1.4738	3.0	36	1.2096
0.9811	4.0	48	0.6866
0.6247	5.0	60	0.5666
0.5433	6.0	72	0.5106
0.4772	7.0	84	0.4398
0.4271	8.0	96	0.3991
0.3906	9.0	108	0.3674
0.3565	10.0	120	0.3397
0.3301	11.0	132	0.2913
0.2869	12.0	144	0.2633
0.2616	13.0	156	0.2313
0.2375	14.0	168	0.2168
0.2218	15.0	180	0.1979
0.2127	16.0	192	0.1937
0.2008	17.0	204	0.1870
0.1933	18.0	216	0.1886
0.1857	19.0	228	0.1726
0.1801	20.0	240	0.1682
0.1722	21.0	252	0.1655
0.168	22.0	264	0.1604
0.1644	23.0	276	0.1530
0.1644	24.0	288	0.1574
0.1582	25.0	300	0.1477
0.1551	26.0	312	0.1460
0.1523	27.0	324	0.1458
0.1471	28.0	336	0.1365
0.1463	29.0	348	0.1385
0.1393	30.0	360	0.1364
0.1355	31.0	372	0.1324
0.134	32.0	384	0.1309
0.1315	33.0	396	0.1274
0.1317	34.0	408	0.1243
0.1266	35.0	420	0.1223
0.1248	36.0	432	0.1206
0.1232	37.0	444	0.1211
0.1217	38.0	456	0.1178
0.1208	39.0	468	0.1166
0.1208	40.0	480	0.1171

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2