rajivkale/bert-finetuned-sem_eval-english

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- sem_eval_2018_task_1
+metrics:
+- f1
+- accuracy
+model-index:
+- name: bert-finetuned-sem_eval-english
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: sem_eval_2018_task_1
+      type: sem_eval_2018_task_1
+      config: subtask5.english
+      split: validation
+      args: subtask5.english
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6532935754947141
+    - name: Accuracy
+      type: accuracy
+      value: 0.23927765237020315
+---
+
+<!-- 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-finetuned-sem_eval-english
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the sem_eval_2018_task_1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3278
+- F1: 0.6533
+- Roc Auc: 0.7575
+- Accuracy: 0.2393
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| 0.4058        | 1.0   | 855  | 0.3278          | 0.6533 | 0.7575  | 0.2393   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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": "anger",
+    "1": "anticipation",
+    "2": "disgust",
+    "3": "fear",
+    "4": "joy",
+    "5": "love",
+    "6": "optimism",
+    "7": "pessimism",
+    "8": "sadness",
+    "9": "surprise",
+    "10": "trust"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 0,
+    "anticipation": 1,
+    "disgust": 2,
+    "fear": 3,
+    "joy": 4,
+    "love": 5,
+    "optimism": 6,
+    "pessimism": 7,
+    "sadness": 8,
+    "surprise": 9,
+    "trust": 10
+  },
+  "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",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "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 sha256:85820f75ae49cab9e509f958306f6824fe2d934e4598f92c56648a66e4f95772
+size 437986332

runs/Nov16_08-43-10_c559dbd62d9c/events.out.tfevents.1700124249.c559dbd62d9c.1492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9019e1e05886ab0d4cee586dc4bfaf04c983df0f6c8150dac723fefddbb6acb1
+size 5675

runs/Nov16_08-43-10_c559dbd62d9c/events.out.tfevents.1700125351.c559dbd62d9c.1492.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ae6c1a7e0bfd02f3d801a9906c8104a28dbb68354d901642ae5fb6d23f9e47
+size 508

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 sha256:5f10b7963451d14ff72e38cfa287583f903aa2aa6cd99694b3f5bc3a223d6e78
+size 4600