add model

README.md

@@ -17,7 +17,7 @@ model_index:
     metric:
       name: Accuracy
       type: accuracy
-      value: 0.951370041268543
+      value: 0.9411086738297951
 ---
 
 <!-- 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: 0.2619
-- Precision: 0.8157
-- Recall: 0.7934
-- F1: 0.8044
-- Accuracy: 0.9514
+- Loss: 0.2071
+- Precision: 0.7502
+- Recall: 0.7385
+- F1: 0.7443
+- Accuracy: 0.9411
 
 ## Model description
 
@@ -51,27 +51,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 207  | 0.2845          | 0.7431    | 0.6314 | 0.6827 | 0.9225   |
-| No log        | 2.0   | 414  | 0.2082          | 0.7766    | 0.7134 | 0.7436 | 0.9396   |
-| 0.2949        | 3.0   | 621  | 0.1992          | 0.7699    | 0.7596 | 0.7647 | 0.9439   |
-| 0.2949        | 4.0   | 828  | 0.2044          | 0.7485    | 0.7908 | 0.7691 | 0.9456   |
-| 0.0896        | 5.0   | 1035 | 0.2129          | 0.7827    | 0.7778 | 0.7802 | 0.9476   |
-| 0.0896        | 6.0   | 1242 | 0.2330          | 0.7893    | 0.7882 | 0.7887 | 0.9485   |
-| 0.0896        | 7.0   | 1449 | 0.2337          | 0.8026    | 0.7947 | 0.7986 | 0.9504   |
-| 0.0334        | 8.0   | 1656 | 0.2579          | 0.8111    | 0.7850 | 0.7978 | 0.9503   |
-| 0.0334        | 9.0   | 1863 | 0.2792          | 0.8263    | 0.7830 | 0.8041 | 0.9510   |
-| 0.0152        | 10.0  | 2070 | 0.2619          | 0.8157    | 0.7934 | 0.8044 | 0.9514   |
+| No log        | 1.0   | 104  | 0.3002          | 0.6859    | 0.5930 | 0.6361 | 0.9171   |
+| No log        | 2.0   | 208  | 0.2449          | 0.7509    | 0.6422 | 0.6923 | 0.9287   |
+| No log        | 3.0   | 312  | 0.2165          | 0.7557    | 0.7062 | 0.7301 | 0.9378   |
+| No log        | 4.0   | 416  | 0.2148          | 0.7402    | 0.7398 | 0.7400 | 0.9388   |
+| 0.2565        | 5.0   | 520  | 0.2071          | 0.7502    | 0.7385 | 0.7443 | 0.9411   |
 
 
 ### Framework versions

config.json

@@ -9,16 +9,16 @@
   "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"
+    "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"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408ab60347d2161cf875856c1d42954cece5df1493039a9b4a441cafda01ea18
+oid sha256:ec7b9a76d0659ac4fa7dfd90789ea31addd81861c9cb485282eb9607256138da
 size 435681969

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb6091d29981239ada696d08d7ffe35b489163a49f6c6e0462f88e10f9294eb
+oid sha256:6b35accb70711230c2bc8838c7735dc30698cdca306d100123e49278684e1394
 size 2671