New model

config.json

@@ -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
-27.28,43.71,80.30,89.10,95.55,98.60,crossencoder-distilcamembert-base-mmarcoFR

mmarco_smallldev_scores.csv

@@ -0,0 +1,7 @@
+epoch,steps,cutoff,mrr,recall,r-precision
+0,20000,5,0.30462989493791787,0.459479465138491,0.20711556829035338
+0,20000,10,0.3186483490244235,0.5632760267430754,0.20711556829035338
+0,20000,20,0.32517350074655005,0.6558858643744031,0.20711556829035338
+0,20000,50,0.32896636702501525,0.7735434574976122,0.20711556829035338
+0,20000,100,0.32994323362411027,0.8439469914040114,0.20711556829035338
+0,20000,500,0.33052651004314615,0.9614971346704871,0.20711556829035338

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d26a7261ecd42aa89f5a6837c38d2f8baa467739b414ca2ae66213533cea90
-size 272398684
+oid sha256:54dd89623bc34d136d6254b5e92b9238dd5dab7398496b71a86869a66f9c15b5
+size 272394484

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65d8ec5eebab10f0612153bb96c72a431789f08a979094582893116dc6107d72
-size 272422133

special_tokens_map.json

@@ -9,7 +9,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
@@ -75,7 +75,7 @@
       "single_word": false,
       "lstrip": true,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     }
   ],
@@ -98,7 +98,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -184,7 +185,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",
@@ -128210,6 +128212,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,4 +1,62 @@
 {
+  "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
+    },
+    "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
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<s>NOTUSED",
     "</s>NOTUSED"
@@ -7,15 +65,8 @@
   "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>",
   "sp_model_kwargs": {},