Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0466
-- Validation Loss: 0.0994
-- Epoch: 2
+- Train Loss: 0.1630
+- Validation Loss: 0.1326
+- Epoch: 0
 
 ## Model description
 
@@ -43,14 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.1763     | 0.1084          | 0     |
-| 0.0693     | 0.0963          | 1     |
-| 0.0466     | 0.0994          | 2     |
+| 0.1630     | 0.1326          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
+- Transformers 4.32.1
 - TensorFlow 2.12.0
-- Datasets 2.14.1
+- Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -10,81 +10,81 @@
   "hidden_dim": 3072,
   "id2label": {
     "0": "O",
-    "1": "B-CARDINAL",
-    "2": "B-DATE",
-    "3": "I-DATE",
-    "4": "B-PERSON",
-    "5": "I-PERSON",
-    "6": "B-NORP",
-    "7": "B-GPE",
-    "8": "I-GPE",
-    "9": "B-LAW",
-    "10": "I-LAW",
-    "11": "B-ORG",
-    "12": "I-ORG",
-    "13": "B-PERCENT",
-    "14": "I-PERCENT",
-    "15": "B-ORDINAL",
-    "16": "B-MONEY",
-    "17": "I-MONEY",
-    "18": "B-WORK_OF_ART",
-    "19": "I-WORK_OF_ART",
-    "20": "B-FAC",
-    "21": "B-TIME",
-    "22": "I-CARDINAL",
-    "23": "B-LOC",
-    "24": "B-QUANTITY",
-    "25": "I-QUANTITY",
-    "26": "I-NORP",
-    "27": "I-LOC",
-    "28": "B-PRODUCT",
-    "29": "I-TIME",
-    "30": "B-EVENT",
-    "31": "I-EVENT",
-    "32": "I-FAC",
-    "33": "B-LANGUAGE",
-    "34": "I-PRODUCT",
-    "35": "I-ORDINAL",
+    "1": "B-PERSON",
+    "2": "I-PERSON",
+    "3": "B-NORP",
+    "4": "I-NORP",
+    "5": "B-FAC",
+    "6": "I-FAC",
+    "7": "B-ORG",
+    "8": "I-ORG",
+    "9": "B-GPE",
+    "10": "I-GPE",
+    "11": "B-LOC",
+    "12": "I-LOC",
+    "13": "B-PRODUCT",
+    "14": "I-PRODUCT",
+    "15": "B-DATE",
+    "16": "I-DATE",
+    "17": "B-TIME",
+    "18": "I-TIME",
+    "19": "B-PERCENT",
+    "20": "I-PERCENT",
+    "21": "B-MONEY",
+    "22": "I-MONEY",
+    "23": "B-QUANTITY",
+    "24": "I-QUANTITY",
+    "25": "B-ORDINAL",
+    "26": "I-ORDINAL",
+    "27": "B-CARDINAL",
+    "28": "I-CARDINAL",
+    "29": "B-EVENT",
+    "30": "I-EVENT",
+    "31": "B-WORK_OF_ART",
+    "32": "I-WORK_OF_ART",
+    "33": "B-LAW",
+    "34": "I-LAW",
+    "35": "B-LANGUAGE",
     "36": "I-LANGUAGE"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "B-CARDINAL": 1,
-    "B-DATE": 2,
-    "B-EVENT": 30,
-    "B-FAC": 20,
-    "B-GPE": 7,
-    "B-LANGUAGE": 33,
-    "B-LAW": 9,
-    "B-LOC": 23,
-    "B-MONEY": 16,
-    "B-NORP": 6,
-    "B-ORDINAL": 15,
-    "B-ORG": 11,
-    "B-PERCENT": 13,
-    "B-PERSON": 4,
-    "B-PRODUCT": 28,
-    "B-QUANTITY": 24,
-    "B-TIME": 21,
-    "B-WORK_OF_ART": 18,
-    "I-CARDINAL": 22,
-    "I-DATE": 3,
-    "I-EVENT": 31,
-    "I-FAC": 32,
-    "I-GPE": 8,
+    "B-CARDINAL": 27,
+    "B-DATE": 15,
+    "B-EVENT": 29,
+    "B-FAC": 5,
+    "B-GPE": 9,
+    "B-LANGUAGE": 35,
+    "B-LAW": 33,
+    "B-LOC": 11,
+    "B-MONEY": 21,
+    "B-NORP": 3,
+    "B-ORDINAL": 25,
+    "B-ORG": 7,
+    "B-PERCENT": 19,
+    "B-PERSON": 1,
+    "B-PRODUCT": 13,
+    "B-QUANTITY": 23,
+    "B-TIME": 17,
+    "B-WORK_OF_ART": 31,
+    "I-CARDINAL": 28,
+    "I-DATE": 16,
+    "I-EVENT": 30,
+    "I-FAC": 6,
+    "I-GPE": 10,
     "I-LANGUAGE": 36,
-    "I-LAW": 10,
-    "I-LOC": 27,
-    "I-MONEY": 17,
-    "I-NORP": 26,
-    "I-ORDINAL": 35,
-    "I-ORG": 12,
-    "I-PERCENT": 14,
-    "I-PERSON": 5,
-    "I-PRODUCT": 34,
-    "I-QUANTITY": 25,
-    "I-TIME": 29,
-    "I-WORK_OF_ART": 19,
+    "I-LAW": 34,
+    "I-LOC": 12,
+    "I-MONEY": 22,
+    "I-NORP": 4,
+    "I-ORDINAL": 26,
+    "I-ORG": 8,
+    "I-PERCENT": 20,
+    "I-PERSON": 2,
+    "I-PRODUCT": 14,
+    "I-QUANTITY": 24,
+    "I-TIME": 18,
+    "I-WORK_OF_ART": 32,
     "O": 0
   },
   "max_position_embeddings": 512,
@@ -97,6 +97,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.1",
   "vocab_size": 28996
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3aa189e1388cfcd4291022fd1d87c854144dea0f8461b9d5c022c8809c968a
+oid sha256:9f3c1635b257be56bdcf5fa00f3ae1050fd11e02365766a490ccea0da1c153c4
 size 261004560