End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0004
-- Precision: 0.9969
-- Recall: 0.9983
-- F1: 0.9976
-- Accuracy: 0.9998
+- Loss: 0.0007
+- Precision: 0.9968
+- Recall: 0.9981
+- F1: 0.9975
+- Accuracy: 0.9996
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0064        | 1.0   | 47891  | 0.0035          | 0.9860    | 0.9882 | 0.9871 | 0.9990   |
-| 0.0028        | 2.0   | 95782  | 0.0008          | 0.9943    | 0.9978 | 0.9961 | 0.9996   |
-| 0.0006        | 3.0   | 143673 | 0.0004          | 0.9969    | 0.9983 | 0.9976 | 0.9998   |
+| 0.0095        | 1.0   | 47891  | 0.0049          | 0.9828    | 0.9859 | 0.9844 | 0.9985   |
+| 0.0024        | 2.0   | 95782  | 0.0018          | 0.9938    | 0.9959 | 0.9948 | 0.9994   |
+| 0.0014        | 3.0   | 143673 | 0.0007          | 0.9968    | 0.9981 | 0.9975 | 0.9996   |
 
 
 ### Framework versions

config.json

@@ -12,32 +12,30 @@
     "0": "LOCATION",
     "1": "BRAND",
     "2": "TITLE_OBJECT",
-    "3": "TITLE_PERSON",
-    "4": "PERSON",
-    "5": "DESIGNATION",
-    "6": "ORGANIZATION",
-    "7": "ABBREVIATION",
-    "8": "TIME",
-    "9": "NUMBER",
-    "10": "MEASURE",
-    "11": "TERMS",
-    "12": "O"
+    "3": "PERSON",
+    "4": "DESIGNATION",
+    "5": "ORGANIZATION",
+    "6": "ABBREVIATION",
+    "7": "TIME",
+    "8": "NUMBER",
+    "9": "MEASURE",
+    "10": "TERMS",
+    "11": "O"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "ABBREVIATION": 7,
+    "ABBREVIATION": 6,
     "BRAND": 1,
-    "DESIGNATION": 5,
+    "DESIGNATION": 4,
     "LOCATION": 0,
-    "MEASURE": 10,
-    "NUMBER": 9,
-    "O": 12,
-    "ORGANIZATION": 6,
-    "PERSON": 4,
-    "TERMS": 11,
-    "TIME": 8,
-    "TITLE_OBJECT": 2,
-    "TITLE_PERSON": 3
+    "MEASURE": 9,
+    "NUMBER": 8,
+    "O": 11,
+    "ORGANIZATION": 5,
+    "PERSON": 3,
+    "TERMS": 10,
+    "TIME": 7,
+    "TITLE_OBJECT": 2
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3005948e5668a31422ce6e626853c6e97e445849a1fd8f2c5e238ecf7b19de0
-size 539011109
+oid sha256:d22d66fdf6d91a8156411664c6e534f8ebdc278a75745a6479a2de7dca71174b
+size 539008037

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bb76fcb3a6693626fbf1864a086d8fb7507cdeb37c91a929fb145233a21caf
+oid sha256:9ca641e469a8fda4ddea182676e9093801ff4ef0022b90d2e6d1aabb005e8d52
 size 4027