Cielciel/aift-model-review-multiple-label-classification-new

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: 2.2623
-- Accuracy Thresh: 0.9380
+- Loss: 1.1569
+- Accuracy Thresh: 0.8636
 
 ## Model description
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|
-| 1.6787        | 1.0   | 845  | 0.8456          | 0.8252          |
-| 0.749         | 2.0   | 1690 | 0.8447          | 0.8887          |
-| 0.5849        | 3.0   | 2535 | 0.9489          | 0.8968          |
-| 0.4312        | 4.0   | 3380 | 1.1496          | 0.9084          |
-| 0.3469        | 5.0   | 4225 | 1.4157          | 0.9260          |
-| 0.2633        | 6.0   | 5070 | 1.8314          | 0.9277          |
-| 0.2498        | 7.0   | 5915 | 1.9466          | 0.9355          |
-| 0.1782        | 8.0   | 6760 | 1.9609          | 0.9336          |
-| 0.1763        | 9.0   | 7605 | 2.2429          | 0.9350          |
-| 0.1489        | 10.0  | 8450 | 2.2623          | 0.9380          |
+| No log        | 1.0   | 70   | 2.6518          | 0.3893          |
+| No log        | 2.0   | 140  | 1.6987          | 0.6300          |
+| No log        | 3.0   | 210  | 1.3761          | 0.7193          |
+| No log        | 4.0   | 280  | 1.2348          | 0.7807          |
+| No log        | 5.0   | 350  | 1.1667          | 0.8279          |
+| No log        | 6.0   | 420  | 1.1763          | 0.8393          |
+| No log        | 7.0   | 490  | 1.1202          | 0.8450          |
+| 1.8776        | 8.0   | 560  | 1.1149          | 0.8521          |
+| 1.8776        | 9.0   | 630  | 1.1348          | 0.8600          |
+| 1.8776        | 10.0  | 700  | 1.1569          | 0.8636          |
 
 
 ### Framework versions

config.json

@@ -11,25 +11,27 @@
   "id2label": {
     "0": "ads",
     "1": "bugs",
-    "2": "graphic",
-    "3": "gameplay",
-    "4": "others",
-    "5": "request",
-    "6": "neutral",
-    "7": "negative",
-    "8": "positive"
+    "2": "positive",
+    "3": "negative",
+    "4": "graphic",
+    "5": "gameplay",
+    "6": "request",
+    "7": "neutral",
+    "8": "feedback",
+    "9": "others"
   },
   "initializer_range": 0.02,
   "label2id": {
     "ads": 0,
     "bugs": 1,
-    "gameplay": 3,
-    "graphic": 2,
-    "negative": 7,
-    "neutral": 6,
-    "others": 4,
-    "positive": 8,
-    "request": 5
+    "feedback": 8,
+    "gameplay": 5,
+    "graphic": 4,
+    "negative": 3,
+    "neutral": 7,
+    "others": 9,
+    "positive": 2,
+    "request": 6
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f9f591c4ee9081bfe7c867b7fb6e3ab13d92e567f945678c0c80c6e5eb2868
-size 267854100
+oid sha256:9f771c4077b70cef7134de5d0ac0d5145e07fc4ef1ea3e2f33f8a18cdcc50833
+size 267857176

models-new-600/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "ads",
+    "1": "bugs",
+    "2": "positive",
+    "3": "negative",
+    "4": "graphic",
+    "5": "gameplay",
+    "6": "request",
+    "7": "neutral",
+    "8": "feedback",
+    "9": "others"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "ads": 0,
+    "bugs": 1,
+    "feedback": 8,
+    "gameplay": 5,
+    "graphic": 4,
+    "negative": 3,
+    "neutral": 7,
+    "others": 9,
+    "positive": 2,
+    "request": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "vocab_size": 30522
+}

models-new-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f771c4077b70cef7134de5d0ac0d5145e07fc4ef1ea3e2f33f8a18cdcc50833
+size 267857176

models-new-600/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models-new-600/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

models-new-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7b03a35128b5fbd3260767565ab2172354e6653ccf2b69c10415c8dd3d3085
+size 4347

runs/Jan29_03-24-01_aift-review-classification-multiple-label/events.out.tfevents.1706498706.aift-review-classification-multiple-label.3311739.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2fde4d959373577e49d17c83e755e1ce0cdf34495f2a3a508a5665ac053d8ee
+size 8884

runs/Jan29_03-24-01_aift-review-classification-multiple-label/events.out.tfevents.1706498763.aift-review-classification-multiple-label.3311739.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc5c0c4077e8d9fa48f2dd699a81dc82be6ae1a108dd3e6e54c09dcc08ff9c9
+size 418

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399e37f10586ee007aeb3ab014242daf5cb64d25949e32ac4ad083b6470d541f
+oid sha256:ad7b03a35128b5fbd3260767565ab2172354e6653ccf2b69c10415c8dd3d3085
 size 4347