Training in progress, epoch 1

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8764705882352941
+      value: 0.8488967343336276
     - name: Recall
       type: recall
-      value: 0.8969546742209632
+      value: 0.8514518413597734
     - name: F1
       type: f1
-      value: 0.8865943297164859
+      value: 0.8501723680721294
     - name: Accuracy
       type: accuracy
-      value: 0.975923333692258
+      value: 0.9675675675675676
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1908
-- Precision: 0.8765
-- Recall: 0.8970
-- F1: 0.8866
-- Accuracy: 0.9759
+- Loss: nan
+- Precision: 0.8489
+- Recall: 0.8515
+- F1: 0.8502
+- Accuracy: 0.9676
 
 ## Model description
 
@@ -79,8 +79,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0568        | 1.0   | 3922 | 0.1877          | 0.8678    | 0.8893 | 0.8785 | 0.9740   |
-| 0.0314        | 2.0   | 7844 | 0.1908          | 0.8765    | 0.8970 | 0.8866 | 0.9759   |
+| 0.0773        | 1.0   | 3922 | nan             | 0.8505    | 0.8461 | 0.8483 | 0.9668   |
+| 0.0487        | 2.0   | 7844 | nan             | 0.8489    | 0.8515 | 0.8502 | 0.9676   |
 
 
 ### Framework versions

config.json

@@ -17,18 +17,30 @@
     "5": "B-LOC",
     "6": "I-LOC",
     "7": "B-MISC",
-    "8": "I-MISC"
+    "8": "I-MISC",
+    "9": "B-JOB",
+    "10": "I-JOB",
+    "11": "B-MAJ",
+    "12": "I-MAJ",
+    "13": "B-SKILL",
+    "14": "I-SKILL"
   },
   "initializer_range": 0.02,
   "label2id": {
+    "B-JOB": 9,
     "B-LOC": 5,
+    "B-MAJ": 11,
     "B-MISC": 7,
     "B-ORG": 3,
     "B-PER": 1,
+    "B-SKILL": 13,
+    "I-JOB": 10,
     "I-LOC": 6,
+    "I-MAJ": 12,
     "I-MISC": 8,
     "I-ORG": 4,
     "I-PER": 2,
+    "I-SKILL": 14,
     "O": 0
   },
   "max_position_embeddings": 512,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08123b2ccbb1766e374a7117a9d612fc6de821d99a70a6dd5a802a9a896656a6
-size 260825186
+oid sha256:f48f65569c6d4d2debaefcefa7094a70189a3b1ec61489ef18523d684837010c
+size 260843682

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": false,
   "do_lower_case": false,
+  "ignore_mismatched_sizes": true,
   "mask_token": "[MASK]",
   "max_length": 512,
   "model_max_length": 512,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5dc0ef45ea2eb42c6608e194b3813cc705419c2bd0159649d14f608688f4fd3
+oid sha256:8ccaef9483fc239c2eab3324b34ce65e985a51200fb7d2254edabd926c3451b8
 size 4472