sungjin228/GoEmotions_FT

README.md

@@ -0,0 +1,98 @@
+---
+library_name: transformers
+license: mit
+base_model: SamLowe/roberta-base-go_emotions
+tags:
+- generated_from_trainer
+datasets:
+- sem_eval_2018_task_1
+metrics:
+- f1
+- accuracy
+- precision
+- recall
+model-index:
+- name: roberta-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: 0.7207163601161665
+    - name: Accuracy
+      type: accuracy
+      value: 0.2799097065462754
+    - name: Precision
+      type: precision
+      value: 0.7554540842212075
+    - name: Recall
+      type: recall
+      value: 0.6890328551596483
+---
+
+<!-- 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. -->
+
+# roberta-finetuned-sem_eval-english
+
+This model is a fine-tuned version of [SamLowe/roberta-base-go_emotions](https://huggingface.co/SamLowe/roberta-base-go_emotions) on the sem_eval_2018_task_1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3097
+- F1: 0.7207
+- Roc Auc: 0.8127
+- Accuracy: 0.2799
+- Precision: 0.7555
+- Recall: 0.6890
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:---------:|:------:|
+| 0.3684        | 1.0   | 855  | 0.3003          | 0.7060 | 0.7973  | 0.3070   | 0.7749    | 0.6483 |
+| 0.2776        | 2.0   | 1710 | 0.2930          | 0.7082 | 0.7978  | 0.3025   | 0.7823    | 0.6469 |
+| 0.2441        | 3.0   | 2565 | 0.3019          | 0.7111 | 0.8025  | 0.2968   | 0.7684    | 0.6617 |
+| 0.2205        | 4.0   | 3420 | 0.3008          | 0.7140 | 0.8060  | 0.2698   | 0.7618    | 0.6719 |
+| 0.2002        | 5.0   | 4275 | 0.3058          | 0.7184 | 0.8109  | 0.2709   | 0.7555    | 0.6849 |
+| 0.1844        | 6.0   | 5130 | 0.3097          | 0.7207 | 0.8127  | 0.2799   | 0.7555    | 0.6890 |
+| 0.1692        | 7.0   | 5985 | 0.3110          | 0.7159 | 0.8102  | 0.2709   | 0.7482    | 0.6863 |
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "SamLowe/roberta-base-go_emotions",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d77cc6f3efe7c28f0ec234a44868b92ef5b92ea9ed0df2efa784dcd6a12695
+size 498640508

runs/Feb11_11-45-50_8a330a3839fb/events.out.tfevents.1739274353.8a330a3839fb.939.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68a13a6c1dd120a7f351039327d8fe34c4d3095ac5d8869aa35029572664d96
+size 12002

runs/Feb11_11-45-50_8a330a3839fb/events.out.tfevents.1739275894.8a330a3839fb.939.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad9ca3cf71059530b975d49e57f681d3d04c1fc2f0ce197669cf04165092394
+size 611

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9359206fc83b24e4eb429234c786235219600cd04a0795c49ea22fe8be1e827d
+size 5368