Cielciel/aift-model

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,47 @@
+{
+  "_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": "graphic",
+    "3": "gameplay",
+    "4": "others",
+    "5": "request",
+    "6": "neutral",
+    "7": "negative",
+    "8": "positive"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "ads": 0,
+    "bugs": 1,
+    "gameplay": 3,
+    "graphic": 2,
+    "negative": 7,
+    "neutral": 6,
+    "others": 4,
+    "positive": 8,
+    "request": 5
+  },
+  "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
+}

.ipynb_checkpoints/special_tokens_map-checkpoint.json

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

.ipynb_checkpoints/tokenizer_config-checkpoint.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]"
+}

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: 2.1529
-- Accuracy Thresh: 0.9374
+- Loss: 3.1256
+- Accuracy Thresh: 0.9115
 
 ## Model description
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|
-| 1.7187        | 1.0   | 845  | 0.8176          | 0.8261          |
-| 0.7417        | 2.0   | 1690 | 0.7961          | 0.8918          |
-| 0.5647        | 3.0   | 2535 | 0.9633          | 0.9031          |
-| 0.441         | 4.0   | 3380 | 1.1189          | 0.9162          |
-| 0.3397        | 5.0   | 4225 | 1.4119          | 0.9260          |
-| 0.2637        | 6.0   | 5070 | 1.8281          | 0.9270          |
-| 0.2387        | 7.0   | 5915 | 1.8851          | 0.9309          |
-| 0.1711        | 8.0   | 6760 | 1.8036          | 0.9349          |
-| 0.1723        | 9.0   | 7605 | 2.1980          | 0.9373          |
-| 0.1573        | 10.0  | 8450 | 2.1529          | 0.9374          |
+| 2.2235        | 1.0   | 584  | 1.2682          | 0.7171          |
+| 1.1638        | 2.0   | 1168 | 1.1630          | 0.8122          |
+| 0.8698        | 3.0   | 1752 | 1.3732          | 0.8635          |
+| 0.7107        | 4.0   | 2336 | 1.5609          | 0.8770          |
+| 0.542         | 5.0   | 2920 | 1.9944          | 0.8927          |
+| 0.3618        | 6.0   | 3504 | 2.2950          | 0.9012          |
+| 0.2842        | 7.0   | 4088 | 2.5621          | 0.9018          |
+| 0.2358        | 8.0   | 4672 | 2.8400          | 0.9079          |
+| 0.2135        | 9.0   | 5256 | 3.1208          | 0.9111          |
+| 0.1731        | 10.0  | 5840 | 3.1256          | 0.9115          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8caf4c37ef8ce97e1f6151c848981dc7a26124e352c48bdd842ad52ecca3387
+oid sha256:1e244b630a1a449882c108a4cf9dc5b400efb23c36f75c7d94672b1f5a620f12
 size 267854100

runs/Jan29_07-41-58_aift-review-classification-multiple-label/events.out.tfevents.1706514135.aift-review-classification-multiple-label.3346014.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9207268286c7605a78a1ac4827fd8cb27c7f5a1772830c84fc010f4a5e6f54e2
+size 10309

runs/Jan29_07-41-58_aift-review-classification-multiple-label/events.out.tfevents.1706514641.aift-review-classification-multiple-label.3346014.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7eac90f5a1d572388d8c025e38f1a1d02f1957cd4dc159c1dc1ca7c54bac05e
+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 sha256:93588cb226d8a418dfec41852cb1c020ae33f8e741f963d3823d1fafbdde5701
+oid sha256:4329ba40331f0e6daf1800e86449eb3954f36410428853becb49723c31dda78a
 size 4219