You can deploy this model and start earning money today!

levshechter/
proximity_cs_model_with_test

Name: proximity_cs_model_with_test
Availability: InStock

Views

No views yet

proximity_cs_model_with_test

This model is a fine-tuned version of OMRIDRORI/mbert-tibetan-continual-unicode-240k on an unknown 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: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 25
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Proximity F1	Proximity Recall	Proximity Precision	Exact Matches	Missed Switches	False Switches	Matches At 1 Words	Matches At 6 Words	Matches At 9 Words	Matches At 10 Words
0.3554	7.6923	100	0.3063	0.9314	0.0892	0.3119	0.0543	1.0	0.0513	19.7179	0.0513	0.0256	0.0256	0.0769
0.0729	15.3846	200	0.2531	0.9791	0.1595	0.2241	0.1791	0.6923	0.4872	5.5128	0.0	0.0	0.0513	0.0
0.0156	23.0769	300	0.3626	0.9896	0.2190	0.2370	0.2504	0.6923	0.5385	2.4872	0.0	0.0	0.0	0.0