aift-model-review-multiple-label-classification

README.md

@@ -15,8 +15,8 @@ should 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9723
-- Accuracy Thresh: 0.9618
+- Loss: 0.9914
+- Accuracy Thresh: 0.9336
 
 ## Model description
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|
-| No log        | 1.0   | 281  | 1.0629          | 0.8503          |
-| 1.6753        | 2.0   | 562  | 0.7421          | 0.9170          |
-| 1.6753        | 3.0   | 843  | 0.6251          | 0.9245          |
-| 0.5414        | 4.0   | 1124 | 0.7125          | 0.9447          |
-| 0.5414        | 5.0   | 1405 | 0.8233          | 0.9541          |
-| 0.3283        | 6.0   | 1686 | 0.8517          | 0.9586          |
-| 0.3283        | 7.0   | 1967 | 0.8811          | 0.9616          |
-| 0.2346        | 8.0   | 2248 | 0.9067          | 0.9618          |
-| 0.1694        | 9.0   | 2529 | 0.9668          | 0.9604          |
-| 0.1694        | 10.0  | 2810 | 0.9723          | 0.9618          |
+| No log        | 1.0   | 70   | 0.9565          | 0.8721          |
+| No log        | 2.0   | 140  | 0.8502          | 0.8907          |
+| No log        | 3.0   | 210  | 0.8939          | 0.9064          |
+| No log        | 4.0   | 280  | 0.8814          | 0.9236          |
+| No log        | 5.0   | 350  | 0.8374          | 0.9164          |
+| No log        | 6.0   | 420  | 0.9718          | 0.9286          |
+| No log        | 7.0   | 490  | 0.9207          | 0.9293          |
+| 0.5144        | 8.0   | 560  | 0.9008          | 0.9321          |
+| 0.5144        | 9.0   | 630  | 0.9761          | 0.9321          |
+| 0.5144        | 10.0  | 700  | 0.9914          | 0.9336          |
 
 
 ### Framework versions

config.json

@@ -15,20 +15,22 @@
     "3": "gameplay",
     "4": "others",
     "5": "request",
-    "6": "neutral",
+    "6": "positive",
     "7": "negative",
-    "8": "positive"
+    "8": "neutral",
+    "9": "feedback"
   },
   "initializer_range": 0.02,
   "label2id": {
     "ads": 0,
     "bugs": 1,
+    "feedback": 9,
     "gameplay": 3,
     "graphic": 2,
     "negative": 7,
-    "neutral": 6,
+    "neutral": 8,
     "others": 4,
-    "positive": 8,
+    "positive": 6,
     "request": 5
   },
   "max_position_embeddings": 512,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be7e0f7099f79ece74bf7c000ca321af328f37ab14019e15034229e950f04e2
-size 267854100
+oid sha256:696949c891ef92e79da7f897bdd0730fa3c090df0d5e7aed11a33cddea4a487e
+size 267857176

runs/Feb15_08-57-53_aift-review-classification-multiple-label/events.out.tfevents.1707987478.aift-review-classification-multiple-label.3885.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e079623237bcd1c4ee6ebae20f5ca2daade5b2fa9825ba058c5835b88a7ecd
+size 8773

runs/Feb15_08-57-53_aift-review-classification-multiple-label/events.out.tfevents.1707987534.aift-review-classification-multiple-label.3885.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df28d1006e1e8878a00a7cda983857e5e571f470cdba06157b9da3f2ce8e982
+size 8550

runs/Feb15_08-57-53_aift-review-classification-multiple-label/events.out.tfevents.1707987588.aift-review-classification-multiple-label.3885.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3645893a64354064fb3b72e55b9a1d812818ebaf9ae297f0613df8c5f2609328
+size 418

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16aec7c5de25ec47ab6027f64368c60b8fd836a2254ce003f985b487e616b291
+oid sha256:fddc9291a12d9b3dea425d841be14b755f12fd8f54f8a455a2a3d33637690d3d
 size 4219