End of training

README.md

@@ -1,8 +1,10 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: cmarkea/distilcamembert-base-sentiment
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: fine-tuned-distilbert-base-uncased
   results: []
@@ -13,15 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine-tuned-distilbert-base-uncased
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [cmarkea/distilcamembert-base-sentiment](https://huggingface.co/cmarkea/distilcamembert-base-sentiment) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.6919
-- eval_accuracy: {'accuracy': 0.8823529411764706}
-- eval_f1score: {'f1': 0.8823529411764706}
-- eval_runtime: 1.7269
-- eval_samples_per_second: 9.844
-- eval_steps_per_second: 1.737
-- step: 0
+- Loss: 0.0005
+- Accuracy: {'accuracy': 1.0}
+- F1score: {'f1': 1.0}
 
 ## Model description
 
@@ -49,6 +47,10 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 85
 - num_epochs: 50
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.35.0

config.json

@@ -1,25 +1,29 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "cmarkea/distilcamembert-base-sentiment",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "CamembertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c48a8f4d4a6ba7d2e2ab0ce78639142f3f34eee13d9737d8fa62ea285d345e59
-size 267832560
+oid sha256:1a5564144606d7b989f347b2d2bb36f9018e84995b77a38c9d97bc0883f4dca2
+size 272397560

runs/Nov05_15-32-57_f50f745bb4ea/events.out.tfevents.1699198392.f50f745bb4ea.175.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af4a5fa3b7eb042570566c1e420a3f6dea1d9a4ccba4212ab899e14dd2eaabb
+size 13534

runs/Nov05_15-32-57_f50f745bb4ea/events.out.tfevents.1699198578.f50f745bb4ea.175.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95268910c2f17ffb506baaccc548c6a7f0690463a6e50e5f327034c383a8478
+size 359

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -1,7 +1,19 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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>"
 }

tokenizer_config.json

@@ -1,55 +1,75 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>NOTUSED",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>NOTUSED",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "5": {
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03796e34329323309a49ad77d63cbd5d0f38cea0b517ef0b7fa368a6276cf85d
+oid sha256:c87137a3d47e8938749684e49c9591ba0e0f3f6e02483c97d4ce7d06e84da548
 size 4600