Adapting `distilbert/distilbert-base-uncased` for `wnut_17`.

README.md

@@ -0,0 +1,98 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- wnut_17
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-base-uncased-wnut_17-full
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: wnut_17
+      type: wnut_17
+      config: wnut_17
+      split: test
+      args: wnut_17
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6038781163434903
+    - name: Recall
+      type: recall
+      value: 0.4040778498609824
+    - name: F1
+      type: f1
+      value: 0.484175458078845
+    - name: Accuracy
+      type: accuracy
+      value: 0.9478859390363815
+---
+
+<!-- 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. -->
+
+# distilbert-base-uncased-wnut_17-full
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the wnut_17 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3599
+- Precision: 0.6039
+- Recall: 0.4041
+- F1: 0.4842
+- Accuracy: 0.9479
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- 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 | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 213  | 0.2609          | 0.5911    | 0.3309 | 0.4242 | 0.9420   |
+| No log        | 2.0   | 426  | 0.2808          | 0.5679    | 0.3373 | 0.4233 | 0.9447   |
+| 0.133         | 3.0   | 639  | 0.3328          | 0.6591    | 0.3244 | 0.4348 | 0.9461   |
+| 0.133         | 4.0   | 852  | 0.3302          | 0.5976    | 0.3689 | 0.4562 | 0.9465   |
+| 0.0224        | 5.0   | 1065 | 0.3142          | 0.4955    | 0.4041 | 0.4451 | 0.9445   |
+| 0.0224        | 6.0   | 1278 | 0.3599          | 0.6039    | 0.4041 | 0.4842 | 0.9479   |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-corporation",
+    "2": "I-corporation",
+    "3": "B-creative-work",
+    "4": "I-creative-work",
+    "5": "B-group",
+    "6": "I-group",
+    "7": "B-location",
+    "8": "I-location",
+    "9": "B-person",
+    "10": "I-person",
+    "11": "B-product",
+    "12": "I-product"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-corporation": 1,
+    "B-creative-work": 3,
+    "B-group": 5,
+    "B-location": 7,
+    "B-person": 9,
+    "B-product": 11,
+    "I-corporation": 2,
+    "I-creative-work": 4,
+    "I-group": 6,
+    "I-location": 8,
+    "I-person": 10,
+    "I-product": 12,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f970da5da1a01ab76f4904344378615e2fc8c07b50c697c1afd29c8d6060aad
+size 265503852

runs/Aug31_23-52-36_26ec1493bf73/events.out.tfevents.1725148357.26ec1493bf73.2602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da61fb3000af4594a45cf8fd651a663983ea6599e9a06f20a4f06e2935ee47a8
+size 9414

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:cbf195f4ce79db8a2acdacf927b719eb0ef0b4c75ca541657b637049c72fb1de
+size 5496