End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-multilingual-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: distilbert-suicide-detection-hk
+  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. -->
+
+# distilbert-suicide-detection-hk
+
+This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3105
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 27   | 0.3452          |
+| No log        | 2.0   | 54   | 0.3644          |
+| No log        | 3.0   | 81   | 0.3075          |
+| No log        | 4.0   | 108  | 0.3395          |
+| No log        | 5.0   | 135  | 0.3105          |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a282d8b557b3383c02ba001cbd7f83cc161b088852ab458303a8eb63f7242dc
+size 541317368

runs/May26_17-08-39_2cad317fbdf9/events.out.tfevents.1716743320.2cad317fbdf9.1996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6089363521ca574f9346b4b5e192755319ecd0a55454450deb7b4b776c8dde9c
+size 4744

runs/May26_17-13-24_2cad317fbdf9/events.out.tfevents.1716743605.2cad317fbdf9.1996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e415d57d9a57af400148369af60e5a2f841c0b2434546f0880cb66ba7f54dc
+size 4744

runs/May26_17-14-46_2cad317fbdf9/events.out.tfevents.1716743687.2cad317fbdf9.1996.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b525932d4ef0832ec962b7a2fca326032833b9a662c6bd7c9135bcee0996bd
+size 4744

runs/May26_17-15-16_2cad317fbdf9/events.out.tfevents.1716743717.2cad317fbdf9.1996.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2056631f9c99a20e4735cef0615cfe512137f775166c2b7e1610a8d3381b1052
+size 4744

runs/May26_17-17-00_2cad317fbdf9/events.out.tfevents.1716743821.2cad317fbdf9.1996.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b300a8f32f6a6197820de8f0fd95a38c9121f27fa3bf55135469e76b350cc525
+size 4744

runs/May26_17-17-40_2cad317fbdf9/events.out.tfevents.1716743860.2cad317fbdf9.1996.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7899e604ea5df2aaf0ef3a516240f4b037a92c1d19b441dc47adafb9ba633a6f
+size 4793

runs/May26_17-19-02_2cad317fbdf9/events.out.tfevents.1716743942.2cad317fbdf9.1996.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da16adec9d7c82b328c3ecf0bbf3b93f9f67c1b53c52b98adcd5f16df484e3c5
+size 6529

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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc95bfd5de23b5c40ad5d25f45a53d251622e86089cb594648410328a1680e0
+size 5112