Cielciel/aift-model

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: aift-model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# aift-model
+
+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
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| 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          |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.0.0+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8caf4c37ef8ce97e1f6151c848981dc7a26124e352c48bdd842ad52ecca3387
+size 267854100

runs/Jan29_03-29-51_aift-review-classification-multiple-label/events.out.tfevents.1706498997.aift-review-classification-multiple-label.3221508.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5665f6510aae988b08dcb018b07a25359cf20e5f065fb0a1cae919fb65e09458
+size 11094

runs/Jan29_03-29-51_aift-review-classification-multiple-label/events.out.tfevents.1706499591.aift-review-classification-multiple-label.3221508.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac40634df1ff630e8ff6ee37b6b7e1134417a747192d24600e9e007d22f82242
+size 418

special_tokens_map.json

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

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]"
+}

training_args.bin

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