morten-j/TinyBERT

my_run

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

• Loss: 6.4043

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: 32
• eval_batch_size: 32
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 128
• total_eval_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
7.1589	1.81	50000	6.8011
6.7421	3.62	100000	6.6767
6.6503	5.42	150000	6.6086
6.5951	7.23	200000	6.5605
6.5566	9.04	250000	6.5271
6.5292	10.85	300000	6.5037
6.5069	12.65	350000	6.4839
6.49	14.46	400000	6.4667
6.4759	16.27	450000	6.4552
6.4648	18.08	500000	6.4442
6.4551	19.88	550000	6.4365
6.4475	21.69	600000	6.4278
6.4412	23.5	650000	6.4222
6.4358	25.31	700000	6.4185
6.4313	27.11	750000	6.4134
6.4275	28.92	800000	6.4110
6.425	30.73	850000	6.4079
6.4229	32.54	900000	6.4063
6.4218	34.35	950000	6.4047
6.4204	36.15	1000000	6.4043

Framework versions

• Transformers 4.38.2
• Pytorch 2.3.0a0+ebedce2
• Datasets 2.17.1
• Tokenizers 0.15.2