Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.4950
-- Validation Loss: 2.4342
-- Epoch: 2
+- Train Loss: 3.2918
+- Validation Loss: 3.0479
+- Epoch: 0
 
 ## Model description
 
@@ -42,9 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.2660     | 3.0039          | 0     |
-| 2.8212     | 2.6067          | 1     |
-| 2.4950     | 2.4342          | 2     |
+| 3.2918     | 3.0479          | 0     |
 
 
 ### Framework versions

config.json

@@ -11,6 +11,14 @@
   "id2label": {
     "0": "O",
     "1": "B-product",
+    "2": "I-product",
+    "3": "B-field",
+    "4": "I-field",
+    "5": "B-task",
+    "6": "I-task",
+    "7": "B-researcher",
+    "8": "I-researcher",
+    "9": "B-university",
     "10": "B-programlang",
     "11": "B-algorithm",
     "12": "I-algorithm",
@@ -21,7 +29,6 @@
     "17": "B-organisation",
     "18": "I-organisation",
     "19": "I-metrics",
-    "2": "I-product",
     "20": "B-conference",
     "21": "I-conference",
     "22": "B-country",
@@ -30,46 +37,39 @@
     "25": "B-person",
     "26": "I-person",
     "27": "I-country",
-    "28": "I-location",
-    "3": "B-field",
-    "4": "I-field",
-    "5": "B-task",
-    "6": "I-task",
-    "7": "B-researcher",
-    "8": "I-researcher",
-    "9": "B-university"
+    "28": "I-location"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "B-algorithm": "11",
-    "B-conference": "20",
-    "B-country": "22",
-    "B-field": "3",
-    "B-location": "24",
-    "B-metrics": "16",
-    "B-misc": "13",
-    "B-organisation": "17",
-    "B-person": "25",
-    "B-product": "1",
-    "B-programlang": "10",
-    "B-researcher": "7",
-    "B-task": "5",
-    "B-university": "9",
-    "I-algorithm": "12",
-    "I-conference": "21",
-    "I-country": "27",
-    "I-field": "4",
-    "I-location": "28",
-    "I-metrics": "19",
-    "I-misc": "14",
-    "I-organisation": "18",
-    "I-person": "26",
-    "I-product": "2",
-    "I-programlang": "23",
-    "I-researcher": "8",
-    "I-task": "6",
-    "I-university": "15",
-    "O": "0"
+    "B-algorithm": 11,
+    "B-conference": 20,
+    "B-country": 22,
+    "B-field": 3,
+    "B-location": 24,
+    "B-metrics": 16,
+    "B-misc": 13,
+    "B-organisation": 17,
+    "B-person": 25,
+    "B-product": 1,
+    "B-programlang": 10,
+    "B-researcher": 7,
+    "B-task": 5,
+    "B-university": 9,
+    "I-algorithm": 12,
+    "I-conference": 21,
+    "I-country": 27,
+    "I-field": 4,
+    "I-location": 28,
+    "I-metrics": 19,
+    "I-misc": 14,
+    "I-organisation": 18,
+    "I-person": 26,
+    "I-product": 2,
+    "I-programlang": 23,
+    "I-researcher": 8,
+    "I-task": 6,
+    "I-university": 15,
+    "O": 0
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d5226ede97e7fc427e995d66cbb412ad0c51f6b397859cf3df147f7b74c1da
+oid sha256:c77683f8cfe7efd22c7d5036447ba7044f727697f621062b67ba3ef76acb1425
 size 265666976