add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,111 @@
+---
+language:
+- fr
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- allocine
+widget:
+- text: "Un film magnifique avec un duo d'acteurs excellent."
+- text: "Grosse déception pour ce thriller qui peine à convaincre."
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: camembert-allocine
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: allocine
+      type: allocine
+      config: allocine
+      split: validation
+      args: allocine
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.97535
+    - name: F1
+      type: f1
+      value: 0.9749045558666326
+    - name: Precision
+      type: precision
+      value: 0.9722814498933902
+    - name: Recall
+      type: recall
+      value: 0.9775418538178848
+---
+
+<!-- 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. -->
+
+# camembert-allocine
+
+This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the allocine dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0928
+- Accuracy: 0.9754
+- F1: 0.9749
+- Precision: 0.9723
+- Recall: 0.9775
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |   F1   | Precision | Recall |
+| :-----------: | :---: | :---: | :-------------: | :------: | :----: | :-------: | :----: |
+|    0.1276     |  0.2  |  500  |     0.1187      |  0.9623  | 0.9622 |  0.9462   | 0.9787 |
+|    0.1013     |  0.4  | 1000  |     0.0917      |  0.9683  | 0.9675 |  0.9725   | 0.9625 |
+|    0.1254     |  0.6  | 1500  |     0.0889      |  0.9701  | 0.9698 |  0.9597   | 0.9801 |
+|    0.1004     |  0.8  | 2000  |     0.0792      |  0.9716  | 0.9709 |  0.9727   | 0.9691 |
+|    0.1149     |  1.0  | 2500  |     0.0762      |  0.9727  | 0.9723 |  0.9673   | 0.9773 |
+|    0.0574     |  1.2  | 3000  |     0.0849      |  0.9733  | 0.9729 |  0.9679   | 0.9780 |
+|    0.0394     |  1.4  | 3500  |     0.1026      |  0.9718  | 0.9715 |  0.9595   | 0.9839 |
+|    0.0401     |  1.6  | 4000  |     0.1065      |  0.9698  | 0.9697 |  0.9528   | 0.9872 |
+|    0.0458     |  1.8  | 4500  |     0.0834      |  0.9744  | 0.9739 |  0.9715   | 0.9764 |
+|    0.0554     |  2.0  | 5000  |     0.0873      |  0.9719  | 0.9717 |  0.9594   | 0.9844 |
+|    0.0516     |  2.2  | 5500  |     0.0928      |  0.9754  | 0.9749 |  0.9723   | 0.9775 |
+|    0.0355     |  2.4  | 6000  |     0.1017      |  0.9744  | 0.9741 |  0.9642   | 0.9842 |
+|    0.0227     |  2.6  | 6500  |     0.0983      |  0.9748  | 0.9743 |  0.9729   | 0.9757 |
+|    0.0359     |  2.8  | 7000  |     0.0990      |  0.9747  | 0.9743 |  0.9665   | 0.9823 |
+|    0.0384     |  3.0  | 7500  |     0.1001      |  0.9746  | 0.9742 |  0.9662   | 0.9824 |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb56261d3f2b4685da2b6fa1c0ba1a6b899cefae578120d5d229f5c4023dc4f
+size 442567349

results/all_results.json

@@ -0,0 +1,27 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.97535,
+    "eval_f1": 0.9749045558666326,
+    "eval_loss": 0.09278112649917603,
+    "eval_precision": 0.9722814498933902,
+    "eval_recall": 0.9775418538178848,
+    "eval_runtime": 144.2966,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 138.603,
+    "eval_steps_per_second": 8.663,
+    "test_accuracy": 0.975,
+    "test_f1": 0.9739583333333334,
+    "test_loss": 0.0953332856297493,
+    "test_precision": 0.9731473771856786,
+    "test_recall": 0.9747706422018348,
+    "test_runtime": 144.7582,
+    "test_samples": 20000,
+    "test_samples_per_second": 138.161,
+    "test_steps_per_second": 8.635,
+    "total_flos": 9.043732950372576e+16,
+    "train_loss": 0.07549678431898356,
+    "train_runtime": 12137.3214,
+    "train_samples": 160000,
+    "train_samples_per_second": 39.547,
+    "train_steps_per_second": 0.618
+}

results/eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.97535,
+    "eval_f1": 0.9749045558666326,
+    "eval_loss": 0.09278112649917603,
+    "eval_precision": 0.9722814498933902,
+    "eval_recall": 0.9775418538178848,
+    "eval_runtime": 144.2966,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 138.603,
+    "eval_steps_per_second": 8.663
+}

results/test_results.json

@@ -0,0 +1,11 @@
+{
+    "test_accuracy": 0.975,
+    "test_f1": 0.9739583333333334,
+    "test_loss": 0.0953332856297493,
+    "test_precision": 0.9731473771856786,
+    "test_recall": 0.9747706422018348,
+    "test_runtime": 144.7582,
+    "test_samples": 20000,
+    "test_samples_per_second": 138.161,
+    "test_steps_per_second": 8.635
+}

results/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.043732950372576e+16,
+    "train_loss": 0.07549678431898356,
+    "train_runtime": 12137.3214,
+    "train_samples": 160000,
+    "train_samples_per_second": 39.547,
+    "train_steps_per_second": 0.618
+}

runs/Mar14_21-24-53_job-21a4d5b5-668d-4516-81af-efb9d86b663b/1678829106.2500846/events.out.tfevents.1678829106.job-21a4d5b5-668d-4516-81af-efb9d86b663b.39288.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62e1c603dfec33f323083dab0cba1109f4bb0b5e3d347c63a8d5687ee415a33
+size 5726

runs/Mar14_21-24-53_job-21a4d5b5-668d-4516-81af-efb9d86b663b/events.out.tfevents.1678829106.job-21a4d5b5-668d-4516-81af-efb9d86b663b.39288.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475939791ec8570faab8177283400283e9633a8e7462b981d58e82e00948fbfa
+size 129321

runs/Mar14_21-24-53_job-21a4d5b5-668d-4516-81af-efb9d86b663b/events.out.tfevents.1678841388.job-21a4d5b5-668d-4516-81af-efb9d86b663b.39288.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523aa9e5c940567568a81960a9315fb84dc075defb7442cbd30b32e2cdc94c29
+size 512

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "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>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1cb0f66a04e3316e7c5eb0b4aaecd89b900167bad7c103d4cf256dc53f40a00
+size 442783552

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "camembert-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159ca7271c5eb2c3c8bd4de654c07c9b8b179aaf1ef106cd87e9712a62a8e0cc
+size 3515