add model

README.md

@@ -17,7 +17,7 @@ model_index:
     metric:
       name: Accuracy
       type: accuracy
-      value: 0.9632618605436434
+      value: 0.9314536552422759
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,11 +27,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1682
-- Precision: 0.8153
-- Recall: 0.8353
-- F1: 0.8251
-- Accuracy: 0.9633
+- Loss: 0.2382
+- Precision: 0.6530
+- Recall: 0.6750
+- F1: 0.6638
+- Accuracy: 0.9315
 
 ## Model description
 
@@ -56,22 +56,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 207  | 0.2003          | 0.6991    | 0.7440 | 0.7209 | 0.9415   |
-| No log        | 2.0   | 414  | 0.1597          | 0.7202    | 0.7770 | 0.7475 | 0.9509   |
-| 0.2342        | 3.0   | 621  | 0.1505          | 0.7619    | 0.8012 | 0.7811 | 0.9558   |
-| 0.2342        | 4.0   | 828  | 0.1710          | 0.7822    | 0.8020 | 0.7920 | 0.9564   |
-| 0.082         | 5.0   | 1035 | 0.1434          | 0.7969    | 0.8277 | 0.8120 | 0.9614   |
-| 0.082         | 6.0   | 1242 | 0.1526          | 0.8001    | 0.8350 | 0.8171 | 0.9625   |
-| 0.082         | 7.0   | 1449 | 0.1590          | 0.8061    | 0.8384 | 0.8219 | 0.9633   |
-| 0.0353        | 8.0   | 1656 | 0.1616          | 0.8143    | 0.8296 | 0.8219 | 0.9634   |
-| 0.0353        | 9.0   | 1863 | 0.1684          | 0.8167    | 0.8367 | 0.8265 | 0.9631   |
-| 0.017         | 10.0  | 2070 | 0.1682          | 0.8153    | 0.8353 | 0.8251 | 0.9633   |
+| No log        | 1.0   | 207  | 0.2382          | 0.6530    | 0.6750 | 0.6638 | 0.9315   |
 
 
 ### Framework versions

config.json

@@ -9,30 +9,30 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9"
+    "B-deriv-per": 9,
+    "B-loc": 5,
+    "B-misc": 7,
+    "B-org": 3,
+    "B-per": 1,
+    "I-loc": 6,
+    "I-misc": 8,
+    "I-org": 4,
+    "I-per": 2,
+    "O": 0
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
+    "0": "O",
+    "1": "B-per",
+    "2": "I-per",
+    "3": "B-org",
+    "4": "I-org",
+    "5": "B-loc",
+    "6": "I-loc",
+    "7": "B-misc",
+    "8": "I-misc",
+    "9": "B-deriv-per"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2f955654d8606fc5cc5af76369339352e021b37404a58c745e84ddbb3683cc
+oid sha256:0f5a71eb21e6f5326a92e92156607df011dd7c974fb6b3bdd37dc99526745519
 size 430992881

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768a0d855af91baffae3b37012f6d08c5fb6fc0059e6f4dd713a05efb2761d9c
+oid sha256:4eec6234f83c50de0bb5ced5c6d4fd8e62155df3e318d5fce3e25778ba79dd34
 size 2671