bert_12_layer_model_v2_complete_training_new_48_KD

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 418.2312
• Accuracy: 0.1802

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: 1e-05
• train_batch_size: 36
• eval_batch_size: 36
• seed: 10
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10000
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
846.7844	0.06	10000	799.2012	0.1433
603.1405	0.12	20000	597.2043	0.1455
552.8343	0.18	30000	549.4058	0.1455
525.8206	0.25	40000	523.2474	0.1455
508.5397	0.31	50000	508.2666	0.1467
495.479	0.37	60000	494.1740	0.1454
485.269	0.43	70000	483.4185	0.1459
474.9876	0.49	80000	475.5062	0.1475
464.3079	0.55	90000	460.0214	0.1507
455.1477	0.61	100000	451.2754	0.1553
444.9362	0.68	110000	441.2908	0.1596
438.575	0.74	120000	432.5171	0.1660
429.8774	0.8	130000	425.1851	0.1693
421.0561	0.86	140000	418.2312	0.1802

Framework versions

• Transformers 4.30.1
• Pytorch 1.14.0a0+410ce96
• Datasets 2.12.0
• Tokenizers 0.13.3