bert-large-uncased-nsp-1000-1e-06-8

This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6890

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-06
• train_batch_size: 32
• eval_batch_size: 1024
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	32	0.8110
No log	2.0	64	0.7445
No log	3.0	96	0.7191
No log	4.0	128	0.7108
No log	5.0	160	0.7060
No log	6.0	192	0.7057
0.7497	7.0	224	0.7024
0.7497	8.0	256	0.6986
0.7497	9.0	288	0.6970
0.7497	10.0	320	0.6964
0.7497	11.0	352	0.6958
0.7497	12.0	384	0.6953
0.7028	13.0	416	0.6947
0.7028	14.0	448	0.6941
0.7028	15.0	480	0.6936
0.7028	16.0	512	0.6931
0.7028	17.0	544	0.6927
0.7028	18.0	576	0.6920
0.6948	19.0	608	0.6916
0.6948	20.0	640	0.6913
0.6948	21.0	672	0.6908
0.6948	22.0	704	0.6906
0.6948	23.0	736	0.6903
0.6948	24.0	768	0.6899
0.6891	25.0	800	0.6897
0.6891	26.0	832	0.6895
0.6891	27.0	864	0.6893
0.6891	28.0	896	0.6891
0.6891	29.0	928	0.6891
0.6891	30.0	960	0.6890

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1