Upload ITER

README.md

@@ -17,7 +17,7 @@ model-index:
         metrics:
           - name: F1
             type: f1
-            value: 0.000
+            value: 80.821
 ---
 
 
@@ -27,7 +27,7 @@ This model checkpoint is part of the collection of models published alongside ou
 [accepted at EMNLP 2024](https://aclanthology.org/2024.findings-emnlp.655/).<br>
 To ease reproducibility and enable open research, our source code has been published on [GitHub](https://github.com/fleonce/iter).
 
-This model achieved an F1 score of `0.000` on dataset `genia`
+This model achieved an F1 score of `80.821` on dataset `genia`
 
 ### Using ITER in your code
 
@@ -39,9 +39,9 @@ pip install git+https://github.com/fleonce/iter
 
 To use our model, refer to the following code:
 ```python
-from iter import ITERForRelationExtraction
+from iter import ITER
 
-model = ITERForRelationExtraction.from_pretrained("fleonce/iter-genia-deberta-large")
+model = ITER.from_pretrained("fleonce/iter-genia-deberta-large")
 tokenizer = model.tokenizer
 
 encodings = tokenizer(
@@ -85,7 +85,7 @@ We publish checkpoints for the models performing best on the following datasets:
 For each dataset, we selected the best performing checkpoint out of the 5 training runs we performed during training.
 This model was trained with the following hyperparameters:
 
-- Seed: `a/cfg/scierc/small_lr_symrel_negsample_d_ff_0.json`
+- Seed: `2`
 - Config: `genia/small_lr_d_ff_150`
 - PyTorch `2.3.0` with CUDA `11.8` and precision `torch.float32`
 - GPU: `1 NVIDIA H100 SXM 80 GB GPU`
@@ -95,9 +95,10 @@ for reproducibility.
 
 To train this model, refer to the following command:
 ```shell
-python3 train.py --dataset genia/small_lr_d_ff_150 --transformer microsoft/deberta-v3-large --seed a/cfg/scierc/small_lr_symrel_negsample_d_ff_0.json
+python3 train.py --dataset genia/small_lr_d_ff_150 --transformer microsoft/deberta-v3-large --seed 2
 ```
 
 ```text
 @inproceedings{citation}
 ```
+