End of training

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: roberta-base-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. -->
+
+# roberta-base-finetuned-depression
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6580
+- Precision: 0.8962
+- Recall: 0.9023
+- F1: 0.8983
+- Accuracy: 0.9062
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 469  | 0.4520          | 0.8637    | 0.7997 | 0.8216 | 0.8635   |
+| 0.5796        | 2.0   | 938  | 0.6088          | 0.9063    | 0.8592 | 0.8733 | 0.8849   |
+| 0.3217        | 3.0   | 1407 | 0.4402          | 0.8921    | 0.8964 | 0.8936 | 0.9030   |
+| 0.2159        | 4.0   | 1876 | 0.6420          | 0.8725    | 0.8890 | 0.8789 | 0.8955   |
+| 0.1496        | 5.0   | 2345 | 0.6017          | 0.8875    | 0.8973 | 0.8908 | 0.9019   |
+| 0.0827        | 6.0   | 2814 | 0.6586          | 0.8804    | 0.9009 | 0.8895 | 0.9009   |
+| 0.0504        | 7.0   | 3283 | 0.6580          | 0.8962    | 0.9023 | 0.8983 | 0.9062   |
+| 0.05          | 8.0   | 3752 | 0.7374          | 0.8859    | 0.9013 | 0.8925 | 0.9030   |
+| 0.0394        | 9.0   | 4221 | 0.7348          | 0.8746    | 0.9043 | 0.8880 | 0.9019   |
+| 0.0241        | 10.0  | 4690 | 0.7371          | 0.8773    | 0.9027 | 0.8883 | 0.9030   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,38 @@
+{
+  "_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": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "MODERATE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "MODERATE": 2,
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "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": "4.41.2",
+  "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 sha256:4994a6dc534070955925b3e824c53acc95f558b93b279e58fdd247cb2cbaa9b2
+size 498615900

runs/Jun22_10-42-23_e7237f170ce3/events.out.tfevents.1719052947.e7237f170ce3.13866.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d492088efc1d676891bf9f54a2415b7a7d5de06287066b971f1b06e8786de391
+size 11995

runs/Jun22_10-42-23_e7237f170ce3/events.out.tfevents.1719054087.e7237f170ce3.13866.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008ad0f5999c86d660242bef91ecb46d4412a67a7c938a00d7565e4b2dbedb8e
+size 560

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:b61f227ad7d8563830a5cc50f8ea34c3d835498089b5cffa8b77514885198aad
+size 5176