lebarnon/GPT2-CompareTransformers-Imdb

README.md

@@ -0,0 +1,99 @@
+---
+license: mit
+base_model: gpt2
+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: 0.9330666661262512
+    - name: Precision
+      type: precision
+      value: 0.9330666661262512
+    - name: Recall
+      type: recall
+      value: 0.9330666661262512
+    - name: F1
+      type: f1
+      value: 0.9330666661262512
+---
+
+<!-- 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 [gpt2](https://huggingface.co/gpt2) on the imdb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2797
+- Accuracy: 0.9331
+- Precision: 0.9331
+- Recall: 0.9331
+- F1: 0.9331
+- Auroc: 0.9810
+
+## 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 | Accuracy | Auroc  | F1     | Validation Loss | Precision | Recall |
+|:-------------:|:-----:|:----:|:--------:|:------:|:------:|:---------------:|:---------:|:------:|
+| 0.1436        | 0.46  | 500  | 0.8935   | 0.9751 | 0.8935 | 0.2923          | 0.8935    | 0.8935 |
+| 0.1621        | 0.91  | 1000 | 0.9261   | 0.9789 | 0.9261 | 0.1984          | 0.9261    | 0.9261 |
+| 0.2196        | 1.37  | 1500 | 0.9289   | 0.9810 | 0.9289 | 0.2082          | 0.9289    | 0.9289 |
+| 0.1457        | 1.83  | 2000 | 0.9325   | 0.9816 | 0.9325 | 0.2282          | 0.9325    | 0.9325 |
+| 0.1103        | 2.29  | 2500 | 0.9305   | 0.9806 | 0.9305 | 0.3201          | 0.9305    | 0.9305 |
+| 0.0679        | 2.74  | 3000 | 0.2797   | 0.9331 | 0.9331 | 0.9331          | 0.9331    | 0.9810 |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 50258
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e59dd1b1046458811ce6be20c7cf21b931413261435485bcdb93dbfe8ae054
+size 497815006

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382fe90b4a7a3103650dea0d1e73701b5623c7fba4394872772a8853a60be8d5
+size 5944