GLiNER-Large (Reproduce) Model 4000 iter
This model is a reproduce version of GLiNER-large, the training hyperparameters are different from the original model.
Hyperparameters
The detail of training hyperparameters can see in deberta.yaml
.
Except for config in deberta.yaml
, i manually set the lr_scheduler_type
to cosine_with_min_lr
and lr_scheduler_kwargs
to {"min_lr_rate": 0.01}
in train.py
:
training_args = TrainingArguments(
...
lr_scheduler_type="cosine_with_min_lr",
lr_scheduler_kwargs={"min_lr_rate": 0.01},
...
)
NOTE: The result is not stable, i guess the random shuffle of the dataset is the reason.
Weights
Here are two weights, one is the final model after 4k iterations, which has the best performance on the zero-shot evaluation, and the other is the model after full training.
Model | link | AI | literature | music | politics | science | movie | restaurant | Average |
---|---|---|---|---|---|---|---|---|---|
iter_4000 | ๐ค | 56.7 | 65.1 | 69.6 | 74.2 | 60.9 | 60.6 | 39.7 | 61.0 |
iter_10000 | ๐ค | 55.1 | 62.9 | 68.3 | 71.6 | 57.3 | 58.4 | 40.5 | 59.2 |
Paper | ๐ค | 57.2 | 64.4 | 69.6 | 72.6 | 62.6 | 57.2 | 42.9 | 60.9 |
Using repo
- Downloads last month
- 1
Inference API (serverless) does not yet support gliner models for this pipeline type.