End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the tner/bionlp2004 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5181
+- Loss: 0.1835
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 13   | 0.6539          |
-| No log        | 2.0   | 26   | 0.5181          |
+| No log        | 1.0   | 125  | 0.2164          |
+| No log        | 2.0   | 250  | 0.1835          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense",
     "key",
     "value",
-    "query",
-    "dense"
+    "query"
   ],
   "task_type": "TOKEN_CLS"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba12c732872a18d7d93606eaf8f8f0102463eae43ce695392957af1e845206e
+oid sha256:e5417de25ed6af27bdbd67f695b39a682abe743372f367f3a666556c2f0c3dae
 size 28398676

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9216e3b6656b0f5c9c7a10a803beae50a2b2339cb8927c86fe7d63b69bd8f29a
+oid sha256:3e670c11b5cac8ce4827e660853257b6305e1758a7a64632c81249b68005f5fd
 size 4347