Training complete

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3559
-- Precision: 0.5850
-- Recall: 0.4773
-- F1: 0.5257
-- Accuracy: 0.9261
+- Loss: 0.2990
+- Precision: 0.5319
+- Recall: 0.5722
+- F1: 0.5513
+- Accuracy: 0.9084
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 425  | 0.3403          | 0.5637    | 0.3971 | 0.4660 | 0.9172   |
-| No log        | 2.0   | 850  | 0.3708          | 0.6084    | 0.4163 | 0.4943 | 0.9217   |
-| No log        | 3.0   | 1275 | 0.3559          | 0.5850    | 0.4773 | 0.5257 | 0.9261   |
+| No log        | 1.0   | 118  | 0.3671          | 0.3949    | 0.4439 | 0.4180 | 0.8833   |
+| No log        | 2.0   | 236  | 0.3071          | 0.5181    | 0.5481 | 0.5327 | 0.9033   |
+| No log        | 3.0   | 354  | 0.2990          | 0.5319    | 0.5722 | 0.5513 | 0.9084   |
 
 
 ### Framework versions

config.json

@@ -11,34 +11,30 @@
   "hidden_size": 768,
   "id2label": {
     "0": "O",
-    "1": "B-corporation",
-    "2": "I-corporation",
-    "3": "B-creative-work",
-    "4": "I-creative-work",
-    "5": "B-group",
-    "6": "I-group",
-    "7": "B-location",
-    "8": "I-location",
-    "9": "B-person",
-    "10": "I-person",
-    "11": "B-product",
-    "12": "I-product"
+    "1": "B-adr",
+    "2": "B-disease",
+    "3": "B-drug",
+    "4": "B-symptom",
+    "5": "B-finding",
+    "6": "I-adr",
+    "7": "I-disease",
+    "8": "I-drug",
+    "9": "I-symptom",
+    "10": "I-finding"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-corporation": 1,
-    "B-creative-work": 3,
-    "B-group": 5,
-    "B-location": 7,
-    "B-person": 9,
-    "B-product": 11,
-    "I-corporation": 2,
-    "I-creative-work": 4,
-    "I-group": 6,
-    "I-location": 8,
-    "I-person": 10,
-    "I-product": 12,
+    "B-adr": 1,
+    "B-disease": 2,
+    "B-drug": 3,
+    "B-finding": 5,
+    "B-symptom": 4,
+    "I-adr": 6,
+    "I-disease": 7,
+    "I-drug": 8,
+    "I-finding": 10,
+    "I-symptom": 9,
     "O": 0
   },
   "layer_norm_eps": 1e-12,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070385f8385b9bc98c96cd000a63c2b4b5390a635e8167f4012d495173a847c3
-size 430986854
+oid sha256:88061be2739877d67adb7a145f8f5f9b2c077313b5c9c91cb36e8a820f85456e
+size 430980710

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8174243a484f3ed3b53bf57303fa21f529a458f32fc2e9ca7dd4ac000fdecf8a
+oid sha256:6943e2f43accb82c30078a0e5c0152cb35f01cdf62c9a4e1beda38f32bcf392b
 size 4472