PHR_Suicide_Prediction_Roberta_Cleaned_Light

README.md

@@ -0,0 +1,79 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- recall
+- precision
+- f1
+model-index:
+- name: PHR_Suicide_Prediction_Roberta_Cleaned_Light
+  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. -->
+
+# PHR_Suicide_Prediction_Roberta_Cleaned_Light
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0553
+- Accuracy: 0.9869
+- Recall: 0.9846
+- Precision: 0.9904
+- F1: 0.9875
+
+## 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: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.06
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1928        | 0.05  | 500  | 0.2289          | 0.9340   | 0.9062 | 0.9660    | 0.9352 |
+| 0.0833        | 0.1   | 1000 | 0.1120          | 0.9752   | 0.9637 | 0.9888    | 0.9761 |
+| 0.0366        | 0.16  | 1500 | 0.1165          | 0.9753   | 0.9613 | 0.9915    | 0.9762 |
+| 0.071         | 0.21  | 2000 | 0.0973          | 0.9709   | 0.9502 | 0.9940    | 0.9716 |
+| 0.0465        | 0.26  | 2500 | 0.0680          | 0.9829   | 0.9979 | 0.9703    | 0.9839 |
+| 0.0387        | 0.31  | 3000 | 0.1583          | 0.9705   | 0.9490 | 0.9945    | 0.9712 |
+| 0.1061        | 0.37  | 3500 | 0.0685          | 0.9848   | 0.9802 | 0.9907    | 0.9854 |
+| 0.0593        | 0.42  | 4000 | 0.0550          | 0.9872   | 0.9947 | 0.9813    | 0.9879 |
+| 0.0382        | 0.47  | 4500 | 0.0551          | 0.9871   | 0.9912 | 0.9842    | 0.9877 |
+| 0.0831        | 0.52  | 5000 | 0.0502          | 0.9840   | 0.9768 | 0.9927    | 0.9847 |
+| 0.0376        | 0.58  | 5500 | 0.0654          | 0.9865   | 0.9852 | 0.9889    | 0.9871 |
+| 0.0634        | 0.63  | 6000 | 0.0422          | 0.9877   | 0.9897 | 0.9870    | 0.9883 |
+| 0.0235        | 0.68  | 6500 | 0.0553          | 0.9869   | 0.9846 | 0.9904    | 0.9875 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "roberta-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": "suicide",
+    "1": "non-suicide"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "non-suicide": 1,
+    "suicide": 0
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "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 sha256:365902c3b5c740d37564457b0404525eee11f7acfb8a2b2809825a81eff2482b
+size 498612824

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 sha256:96beeec41b418617e646cf99e2f141af1eeda42848cd2ebdd1fc39e63c3c3dec
+size 4920