lebarnon/RoBERTa-CompareTransformers-Imdb

README.md

@@ -0,0 +1,99 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- imdb
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: results
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: imdb
+      type: imdb
+      config: plain_text
+      split: train
+      args: plain_text
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9286666512489319
+    - name: Precision
+      type: precision
+      value: 0.9286666512489319
+    - name: Recall
+      type: recall
+      value: 0.9286666512489319
+    - name: F1
+      type: f1
+      value: 0.9286666512489319
+---
+
+<!-- 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. -->
+
+# results
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the imdb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2691
+- Accuracy: 0.9287
+- Precision: 0.9287
+- Recall: 0.9287
+- F1: 0.9287
+- Auroc: 0.9772
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Auroc  |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 0.1764        | 0.46  | 500  | 0.2698          | 0.9044   | 0.9044    | 0.9044 | 0.9044 | 0.9738 |
+| 0.3348        | 0.91  | 1000 | 0.2755          | 0.9117   | 0.9117    | 0.9117 | 0.9117 | 0.9686 |
+| 0.1478        | 1.37  | 1500 | 0.3275          | 0.9109   | 0.9109    | 0.9109 | 0.9109 | 0.9771 |
+| 0.2051        | 1.83  | 2000 | 0.2575          | 0.9309   | 0.9309    | 0.9309 | 0.9309 | 0.9793 |
+| 0.1435        | 2.29  | 2500 | 0.3140          | 0.9245   | 0.9245    | 0.9245 | 0.9245 | 0.9783 |
+| 0.1425        | 2.74  | 3000 | 0.2691          | 0.9287   | 0.9287    | 0.9287 | 0.9287 | 0.9772 |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30eead246e37325913c3d01e96dd15339235fc0c85f7e6910f386fa200f4002
+size 498655278

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d505b3cd99258aee838b457237f0f555db3790e073ca0f3a0f583b3afcd438ef
+size 5944