yunase/DistilRoBertaModel_emotion_detection

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: distilroberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: emotions_distilroberta
+  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_distilroberta
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5345
+- F1 Micro: 0.6750
+- F1 Macro: 0.5924
+- Accuracy: 0.2078
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 0.7583        | 0.41  | 20   | 0.6581          | 0.5780   | 0.3558   | 0.1055   |
+| 0.6291        | 0.82  | 40   | 0.5893          | 0.6285   | 0.4836   | 0.1424   |
+| 0.5796        | 1.22  | 60   | 0.5759          | 0.6319   | 0.5261   | 0.1618   |
+| 0.5288        | 1.63  | 80   | 0.5409          | 0.6585   | 0.5526   | 0.1430   |
+| 0.5111        | 2.04  | 100  | 0.5339          | 0.6681   | 0.5648   | 0.1961   |
+| 0.4635        | 2.45  | 120  | 0.5291          | 0.6684   | 0.5714   | 0.1786   |
+| 0.4544        | 2.86  | 140  | 0.5282          | 0.6726   | 0.5787   | 0.1618   |
+| 0.4398        | 3.27  | 160  | 0.5281          | 0.6736   | 0.5833   | 0.2052   |
+| 0.3948        | 3.67  | 180  | 0.5309          | 0.6650   | 0.5896   | 0.1890   |
+| 0.41          | 4.08  | 200  | 0.5265          | 0.6785   | 0.5782   | 0.2168   |
+| 0.3722        | 4.49  | 220  | 0.5345          | 0.6750   | 0.5924   | 0.2078   |
+| 0.3617        | 4.9   | 240  | 0.5295          | 0.6769   | 0.5822   | 0.2155   |
+| 0.3362        | 5.31  | 260  | 0.5358          | 0.6696   | 0.5854   | 0.1851   |
+| 0.3204        | 5.71  | 280  | 0.5438          | 0.6762   | 0.5747   | 0.2097   |
+| 0.3194        | 6.12  | 300  | 0.5503          | 0.6764   | 0.5768   | 0.1832   |
+| 0.2921        | 6.53  | 320  | 0.5599          | 0.6734   | 0.5787   | 0.1961   |
+| 0.2938        | 6.94  | 340  | 0.5532          | 0.6753   | 0.5863   | 0.1806   |
+| 0.2708        | 7.35  | 360  | 0.5634          | 0.6735   | 0.5782   | 0.1922   |
+| 0.2625        | 7.76  | 380  | 0.5716          | 0.6727   | 0.5756   | 0.1961   |
+| 0.2565        | 8.16  | 400  | 0.5671          | 0.6739   | 0.5798   | 0.1922   |
+| 0.2403        | 8.57  | 420  | 0.5816          | 0.6688   | 0.5735   | 0.1728   |
+| 0.2466        | 8.98  | 440  | 0.5818          | 0.6739   | 0.5744   | 0.1871   |
+| 0.2331        | 9.39  | 460  | 0.5826          | 0.6722   | 0.5762   | 0.1922   |
+| 0.2233        | 9.8   | 480  | 0.5843          | 0.6738   | 0.5768   | 0.1942   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "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": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "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 sha256:30a335aa1bb97e56ed2e8c475597a0905e97598d6972a39db49fd1ba0e7abfb4
+size 328519964

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86a49d7e22fc240d2336041e6115b41e1af5c87bf9340298937f6d5f72c4847
+size 5048