You can deploy this model and start earning money today!

Dersty/
distilrubert_X5_ner_MLM

Views

No views yet

results_ft

This model is a fine-tuned version of DeepPavlov/distilrubert-base-cased-conversational on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 256
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 4

Training Loss	Epoch	Step	Validation Loss
4.2358	0.25	200	3.5514
3.4076	0.5	400	3.1408
3.0609	0.75	600	2.8831
2.8596	1.0	800	2.7254
2.6537	1.25	1000	2.6169
2.5488	1.5	1200	2.3984
2.4349	1.75	1400	2.3911
2.3377	2.0	1600	2.2564
2.2242	2.25	1800	2.1910
2.1617	2.5	2000	2.1488
2.1151	2.75	2200	2.0530
2.066	3.0	2400	2.0707
1.9841	3.25	2600	1.9644
1.9669	3.5	2800	1.9697
1.9261	3.75	3000	1.9035
1.906	4.0	3200	1.9402