New model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "nreimers/mMiniLMv2-L6-H384-distilled-from-XLMR-Large",
+  "_name_or_path": "unicamp-dl/mMiniLM-L6-v2-mmarco-v2",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
@@ -25,8 +25,9 @@
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.36.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

dev_scores.csv

@@ -1,2 +0,0 @@
-r-precision,mrr@10,recall@10,recall@20,recall@50,recall@100,model
-33.92,49.33,79.00,88.35,94.80,98.20,crossencoder-mMiniLMv2-L6-H384-distilled-from-XLMR-Large-mmarcoFR

mmarco_smallldev_scores.csv

@@ -0,0 +1,7 @@
+epoch,steps,cutoff,mrr,recall,r-precision
+0,20000,5,0.31867956064947467,0.47521489971346703,0.21953199617956065
+0,20000,10,0.333447832810297,0.5840138490926456,0.21953199617956065
+0,20000,20,0.3400716362694083,0.6788681948424069,0.21953199617956065
+0,20000,50,0.34315412209940344,0.7746418338108882,0.21953199617956065
+0,20000,100,0.34405620084323624,0.8383954154727794,0.21953199617956065
+0,20000,500,0.344670392370067,0.9618553008595988,0.21953199617956065

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6409af27ce04becdc16958788f0a0fcb0bd991f3cbf7340db1a0fbe7e041513
-size 427993940
+oid sha256:66f3350c8d3f0a27fca24e7bcd41a71d06d74b7f8879c2a2b4024777acc9a854
+size 427989732

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:583323d2d680875692e528421c6c9fdfeff5b3f29a86be8eede01e98a5076349
-size 428017397

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
-size 17082913
+oid sha256:8dcca5f037c4beb22bb95e204a945e0640e93d283ce622febe906fdf25a146d9
+size 17083009

tokenizer_config.json

@@ -1,19 +1,61 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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>",
+      "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "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>",
+  "max_length": 512,
+  "model_max_length": 256,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }