New model

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>NOTUSED": 32005
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "camembert-base",
+  "_name_or_path": "almanach/camembert-base",
   "architectures": [
     "CamembertForSequenceClassification"
   ],
@@ -27,7 +27,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.36.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 32005

dev_scores.csv

@@ -1,2 +0,0 @@
-r-precision,mrr@10,recall@10,recall@20,recall@50,recall@100,model
-35.65,50.44,82.95,91.50,96.80,98.80,crossencoder-camembert-base-mmarcoFR

mmarco_smallldev_scores.csv

@@ -0,0 +1,6 @@
+epoch,steps,cutoff,mrr,recall,r-precision
+0,20000,5,0.3195487106017192,0.4914517669531996,0.21380133715377267
+0,20000,10,0.33395489380088234,0.5982808022922637,0.21380133715377267
+0,20000,20,0.340528721477873,0.6925382043935052,0.21380133715377267
+0,20000,50,0.3438538366740518,0.7952960840496658,0.21380133715377267
+0,20000,100,0.3446662186199474,0.8534383954154727,0.21380133715377267

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f931066b603cc10af0d660c2e498dc573c1fb3bebdc109d10bb5a258c2136c
-size 442519228
+oid sha256:0a991fc6f0bf126014aecbe313963ea515be39aabb2d8cf10d5ff6927ab3b9a4
+size 442515028

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:324dc3236fb67814bab4d2faccf7293865fa64333c0347a285e812d913c70f34
-size 442564277

special_tokens_map.json

@@ -1,7 +1,8 @@
 {
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED"
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
@@ -77,6 +77,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32005,
+      "content": "<unk>NOTUSED",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -92,7 +101,8 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "add_prefix_space": true
+        "add_prefix_space": true,
+        "prepend_scheme": "always"
       }
     ]
   },
@@ -180,7 +190,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",
@@ -128206,6 +128217,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,21 +1,81 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED"
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
   ],
   "bos_token": "<s>",
   "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
-  },
-  "model_max_length": 512,
+  "mask_token": "<mask>",
+  "model_max_length": 256,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "CamembertTokenizer",