Training in progress, step 500

added_tokens.json

@@ -0,0 +1,10 @@
+{
+  "</s>": 6,
+  "</s>NOTUSED": 2,
+  "<_>": 8,
+  "<mask>": 25004,
+  "<pad>": 1,
+  "<s>": 5,
+  "<s>NOTUSED": 0,
+  "<unk>": 3
+}

config.json

@@ -11,18 +11,8 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "camembert",
@@ -32,7 +22,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 25005

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1e9c323a8daa0de45cccd12ac16532aaa49a41024d0a90d295030f1479ac35
-size 418692841
+oid sha256:d1ed7fad7a2d095cc8c07fbde1369116542fa8d8851835370a177a53bd4aea1a
+size 418689769

special_tokens_map.json

@@ -7,13 +7,7 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"

tokenizer.json

@@ -7,8 +7,8 @@
       "id": 0,
       "content": "<s>NOTUSED",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -25,8 +25,8 @@
       "id": 2,
       "content": "</s>NOTUSED",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -61,8 +61,8 @@
       "id": 8,
       "content": "<_>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -100207,6 +100207,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,4 +1,70 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<s>NOTUSED",
     "</s>NOTUSED",
@@ -8,14 +74,7 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c0c960876fd4ca64bc0b7d2abbd14523d365bb4541f50edcb6cd71138db137
-size 4027
+oid sha256:65ccef507a8cce56f1144b6a1d92c6db392ada4a1be731538cf5e8b3d0bbd396
+size 4091