Adapting `google-bert/bert-base-uncased` for `wnut_17`.

README.md

@@ -0,0 +1,98 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- wnut_17
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-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: 0.6373056994818653
+    - name: Recall
+      type: recall
+      value: 0.34198331788693237
+    - name: F1
+      type: f1
+      value: 0.44511459589867314
+    - name: Accuracy
+      type: accuracy
+      value: 0.9476294301226967
+---
+
+<!-- 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. -->
+
+# bert-base-uncased-wnut_17-full
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the wnut_17 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4356
+- Precision: 0.6373
+- Recall: 0.3420
+- F1: 0.4451
+- Accuracy: 0.9476
+
+## 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  | 0.2799          | 0.6045    | 0.3216 | 0.4198 | 0.9457   |
+| No log        | 2.0   | 426  | 0.3236          | 0.5728    | 0.3392 | 0.4261 | 0.9463   |
+| 0.0468        | 3.0   | 639  | 0.3751          | 0.5924    | 0.3448 | 0.4359 | 0.9472   |
+| 0.0468        | 4.0   | 852  | 0.3713          | 0.5733    | 0.3661 | 0.4468 | 0.9470   |
+| 0.0105        | 5.0   | 1065 | 0.3827          | 0.5741    | 0.3735 | 0.4526 | 0.9479   |
+| 0.0105        | 6.0   | 1278 | 0.4356          | 0.6373    | 0.3420 | 0.4451 | 0.9476   |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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,
+  "intermediate_size": 3072,
+  "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
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db369226d24e3379dd10e15be15e8e3b5981a667e7594de39237b94f380e318
+size 435629924

runs/Sep01_00-24-37_7fbf86d46184/events.out.tfevents.1725150279.7fbf86d46184.2222.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960bbe069c72d4a9d5b7951d3c92aaddcc8c97806e20b0f5d2307de2bdd98b8c
+size 9509

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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51496fb060c2fc9f8040c7a5df767256c0b05a7d417c80ca08469a40f28b71ec
+size 5496