add model

.gitignore

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

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: punct_restore_fr
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 1.0
+---
+
+<!-- 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. -->
+
+# punct_restore_fr
+
+This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0346
+- Precision: 1.0
+- Recall: 1.0
+- F1: 1.0
+- Accuracy: 1.0
+
+## 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: 8
+- seed: 1
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.8.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.8.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 1.0,
+    "eval_f1": 1.0,
+    "eval_loss": 0.03462713584303856,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_runtime": 0.1879,
+    "eval_samples": 100,
+    "eval_samples_per_second": 532.184,
+    "eval_steps_per_second": 69.184,
+    "predict_accuracy": 1.0,
+    "predict_f1": 1.0,
+    "predict_loss": 0.034570880234241486,
+    "predict_precision": 1.0,
+    "predict_recall": 1.0,
+    "predict_runtime": 0.2013,
+    "predict_samples_per_second": 496.83,
+    "predict_steps_per_second": 64.588,
+    "train_loss": 0.1188449223836263,
+    "train_runtime": 17.2449,
+    "train_samples": 800,
+    "train_samples_per_second": 139.172,
+    "train_steps_per_second": 8.698
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "eos_token_id": 6,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-SENT",
+    "1": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-SENT": 0,
+    "O": 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",
+  "transformers_version": "4.8.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 1.0,
+    "eval_f1": 1.0,
+    "eval_loss": 0.03462713584303856,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_runtime": 0.1879,
+    "eval_samples": 100,
+    "eval_samples_per_second": 532.184,
+    "eval_steps_per_second": 69.184
+}

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 1.0,
+    "predict_f1": 1.0,
+    "predict_loss": 0.034570880234241486,
+    "predict_precision": 1.0,
+    "predict_recall": 1.0,
+    "predict_runtime": 0.2013,
+    "predict_samples_per_second": 496.83,
+    "predict_steps_per_second": 64.588
+}

predictions.txt

@@ -0,0 +1,100 @@
+B-SENT O
+B-SENT O
+B-SENT O O O O
+B-SENT O O O O O
+B-SENT O O
+B-SENT O O
+B-SENT O O O O
+B-SENT O
+B-SENT
+B-SENT O O O O O
+B-SENT O O O
+B-SENT O O O O O O O O O O
+B-SENT O O O O O O
+B-SENT O O O O
+B-SENT O O O O
+B-SENT O O
+B-SENT
+B-SENT
+B-SENT O O O O O
+B-SENT O O O O O O O O O
+B-SENT O O
+B-SENT O
+B-SENT
+B-SENT
+B-SENT O O O O
+B-SENT O O O
+B-SENT O O O O
+B-SENT O O O O O O O
+B-SENT O O
+B-SENT O O O O O O O O
+B-SENT
+B-SENT O O O O O O
+B-SENT O
+B-SENT
+B-SENT O O O
+B-SENT O O O
+B-SENT O O O O O O
+B-SENT O O
+B-SENT
+B-SENT O O O O O
+B-SENT O O O O O O O O O
+B-SENT O O O O O
+B-SENT O O O O O O
+B-SENT O O O O O
+B-SENT O O O
+B-SENT O O O O O O
+B-SENT O O
+B-SENT O O O
+B-SENT O O O
+B-SENT O O O
+B-SENT O O O O
+B-SENT O O O
+B-SENT O O O O O O O O O
+B-SENT O O O O O O O
+B-SENT O O O O O
+B-SENT O O
+B-SENT O O O O O O
+B-SENT O O O O O O O O
+B-SENT O O O O O O
+B-SENT O O O O O
+B-SENT O O O O O O O O O
+B-SENT O O
+B-SENT O
+B-SENT O O
+B-SENT O
+B-SENT O O O O
+B-SENT O O O O O O O O
+B-SENT
+B-SENT O O O O O O
+B-SENT O O O O
+B-SENT O O
+B-SENT O O O O O O
+B-SENT O O O O O O O
+B-SENT
+B-SENT O O
+B-SENT
+B-SENT O O
+B-SENT O O O O O O
+B-SENT
+B-SENT O O
+B-SENT O O O O O
+B-SENT O O
+B-SENT O O O O O
+B-SENT O
+B-SENT O O O O
+B-SENT O O O O O
+B-SENT O O O O O
+B-SENT O O O O
+B-SENT O O O
+B-SENT O O O
+B-SENT O
+B-SENT O O O O O
+B-SENT O O O O O O
+B-SENT O O
+B-SENT O O
+B-SENT
+B-SENT O O
+B-SENT O O O O O
+B-SENT O O O O
+B-SENT O O

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6e0d137cd124000abead061cb122109bdb2a2005544d719f6223091860599e
+size 440216305

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.1188449223836263,
+    "train_runtime": 17.2449,
+    "train_samples": 800,
+    "train_samples_per_second": 139.172,
+    "train_steps_per_second": 8.698
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 150,
+      "total_flos": 50259506753664.0,
+      "train_loss": 0.1188449223836263,
+      "train_runtime": 17.2449,
+      "train_samples_per_second": 139.172,
+      "train_steps_per_second": 8.698
+    }
+  ],
+  "max_steps": 150,
+  "num_train_epochs": 3,
+  "total_flos": 50259506753664.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e501ebaafb54fa08b9cc6a6a337a7ed61a65191081ddd5bda8581472f0a7c2
+size 2607