yunase/Bert_emotion_detection

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: emotions_bert
+  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. -->
+
+# emotions_bert
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5151
+- F1 Micro: 0.6887
+- F1 Macro: 0.6024
+- Accuracy: 0.1929
+
+## 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: 0.0001
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1 Micro | F1 Macro | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 0.7549        | 0.4082 | 20   | 0.6455          | 0.6125   | 0.4264   | 0.1243   |
+| 0.6144        | 0.8163 | 40   | 0.5675          | 0.6510   | 0.5188   | 0.1670   |
+| 0.5496        | 1.2245 | 60   | 0.5414          | 0.6747   | 0.5570   | 0.1883   |
+| 0.4878        | 1.6327 | 80   | 0.5191          | 0.6849   | 0.5894   | 0.2104   |
+| 0.4754        | 2.0408 | 100  | 0.5140          | 0.6810   | 0.5909   | 0.2013   |
+| 0.4027        | 2.4490 | 120  | 0.5169          | 0.6849   | 0.5880   | 0.2207   |
+| 0.3986        | 2.8571 | 140  | 0.5151          | 0.6887   | 0.6024   | 0.1929   |
+| 0.3711        | 3.2653 | 160  | 0.5187          | 0.6820   | 0.5991   | 0.2188   |
+| 0.325         | 3.6735 | 180  | 0.5263          | 0.6753   | 0.5928   | 0.1942   |
+| 0.3303        | 4.0816 | 200  | 0.5294          | 0.6900   | 0.5949   | 0.2149   |
+| 0.2801        | 4.4898 | 220  | 0.5420          | 0.6840   | 0.5953   | 0.2097   |
+| 0.2748        | 4.8980 | 240  | 0.5583          | 0.6797   | 0.5861   | 0.2162   |
+| 0.2452        | 5.3061 | 260  | 0.5781          | 0.6758   | 0.5871   | 0.1981   |
+| 0.2253        | 5.7143 | 280  | 0.5889          | 0.6715   | 0.5812   | 0.1929   |
+| 0.226         | 6.1224 | 300  | 0.5955          | 0.6793   | 0.5852   | 0.2207   |
+| 0.1958        | 6.5306 | 320  | 0.6120          | 0.6734   | 0.5861   | 0.2032   |
+| 0.1952        | 6.9388 | 340  | 0.6209          | 0.6744   | 0.5806   | 0.2084   |
+| 0.1758        | 7.3469 | 360  | 0.6339          | 0.6756   | 0.5789   | 0.2136   |
+| 0.1691        | 7.7551 | 380  | 0.6412          | 0.6773   | 0.5779   | 0.2188   |
+| 0.1613        | 8.1633 | 400  | 0.6431          | 0.6761   | 0.5794   | 0.2142   |
+| 0.1486        | 8.5714 | 420  | 0.6532          | 0.6718   | 0.5763   | 0.2104   |
+| 0.1529        | 8.9796 | 440  | 0.6577          | 0.6737   | 0.5747   | 0.2136   |
+| 0.1436        | 9.3878 | 460  | 0.6658          | 0.6734   | 0.5744   | 0.2194   |
+| 0.1399        | 9.7959 | 480  | 0.6640          | 0.6735   | 0.5745   | 0.2188   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,52 @@
+{
+  "_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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "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:dc98fc6e57ed6762e6a00176703b5ba66009aee0aab94550fab5754764c01b0d
+size 437986332

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 sha256:11502710e2f816c467721f23b5c655ca17b583b69b8f515cfd3ea878a5be362e
+size 5112