End of training

README.md

@@ -0,0 +1,85 @@
+---
+license: cc-by-nc-4.0
+base_model: mental/mental-bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: mental-bert-base-uncased-finetuned-depression
+  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. -->
+
+# mental-bert-base-uncased-finetuned-depression
+
+This model is a fine-tuned version of [mental/mental-bert-base-uncased](https://huggingface.co/mental/mental-bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5358
+- Precision: 0.8986
+- Recall: 0.8885
+- F1: 0.8933
+- Accuracy: 0.9158
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 469  | 0.3929          | 0.8744    | 0.8346 | 0.8516 | 0.8849   |
+| 0.4726        | 2.0   | 938  | 0.4405          | 0.9052    | 0.8359 | 0.8660 | 0.8955   |
+| 0.2165        | 3.0   | 1407 | 0.4594          | 0.8627    | 0.8435 | 0.8515 | 0.8891   |
+| 0.1263        | 4.0   | 1876 | 0.5213          | 0.9012    | 0.8781 | 0.8886 | 0.9094   |
+| 0.0719        | 5.0   | 2345 | 0.4879          | 0.9036    | 0.8694 | 0.8851 | 0.9083   |
+| 0.0471        | 6.0   | 2814 | 0.5628          | 0.9185    | 0.8639 | 0.8880 | 0.9104   |
+| 0.0431        | 7.0   | 3283 | 0.5592          | 0.8980    | 0.8731 | 0.8846 | 0.9104   |
+| 0.0402        | 8.0   | 3752 | 0.5948          | 0.9166    | 0.8591 | 0.8848 | 0.9094   |
+| 0.0348        | 9.0   | 4221 | 0.5358          | 0.8986    | 0.8885 | 0.8933 | 0.9158   |
+| 0.0276        | 10.0  | 4690 | 0.6361          | 0.9116    | 0.8619 | 0.8843 | 0.9094   |
+| 0.0281        | 11.0  | 5159 | 0.6535          | 0.9095    | 0.8726 | 0.8897 | 0.9147   |
+| 0.029         | 12.0  | 5628 | 0.6776          | 0.9098    | 0.8673 | 0.8868 | 0.9136   |
+| 0.0188        | 13.0  | 6097 | 0.6940          | 0.9072    | 0.8629 | 0.8829 | 0.9072   |
+| 0.0215        | 14.0  | 6566 | 0.7022          | 0.9168    | 0.8606 | 0.8856 | 0.9115   |
+| 0.0184        | 15.0  | 7035 | 0.6996          | 0.9027    | 0.8687 | 0.8846 | 0.9126   |
+| 0.0204        | 16.0  | 7504 | 0.6990          | 0.9063    | 0.8687 | 0.8861 | 0.9126   |
+| 0.0204        | 17.0  | 7973 | 0.7268          | 0.9103    | 0.8677 | 0.8871 | 0.9115   |
+| 0.0185        | 18.0  | 8442 | 0.7210          | 0.9066    | 0.8766 | 0.8907 | 0.9147   |
+| 0.0181        | 19.0  | 8911 | 0.7346          | 0.9096    | 0.8732 | 0.8902 | 0.9147   |
+| 0.0151        | 20.0  | 9380 | 0.7363          | 0.9090    | 0.8720 | 0.8892 | 0.9136   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mental/mental-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": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "MODERATE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "MODERATE": 2,
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "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 sha256:643f6bfa885d16217d66631b0a99b6add550db784e996197cf7c8238dbfcbc49
+size 437961724

runs/Jun22_12-34-27_c06c4ffc31a4/events.out.tfevents.1719059685.c06c4ffc31a4.189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ce8f08c494209bcd24e0a738d4ca319c5b837c23574fb5960a4ea1d5a8afe4
+size 12065

runs/Jun22_12-34-27_c06c4ffc31a4/events.out.tfevents.1719060772.c06c4ffc31a4.189.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09d3b42f89e20296de99394abdf348214ffab6da980ed245436f2cc37051925
+size 560

runs/Jun22_12-54-01_c06c4ffc31a4/events.out.tfevents.1719060849.c06c4ffc31a4.189.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0e7a80b8536af40f3b788d25c840f84a4233e99697e88d750739b1f79e455e
+size 18684

runs/Jun22_12-54-01_c06c4ffc31a4/events.out.tfevents.1719063192.c06c4ffc31a4.189.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fae328365b0467a7d1669af3c9e8795ae59895c378f6d227c4b3a9657508c51
+size 1032

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,55 @@
+{
+  "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:a69d82984dc9421c7c74aea84640976979689e33f33b63a60446871303acfe05
+size 5176