e5 epoch 2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bhavikardeshna/xlm-roberta-base-vietnamese",
+  "_name_or_path": "mjwong/multilingual-e5-base-xnli-anli",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
@@ -7,33 +7,30 @@
   "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,
   "id2label": {
-    "0": "SUPPORTED",
-    "1": "REFUTED",
-    "2": "NEI"
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "NEI": 2,
-    "REFUTED": 1,
-    "SUPPORTED": 0
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
   },
-  "language": "english",
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
-  "name": "XLMRoberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "problem_type": "multi_label_classification",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.33.0",
   "type_vocab_size": 1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117d69782801d57e9b937275aae0f9efc092900c6b8ab27f852af159d8d237ca
+oid sha256:a353b30f34cb9175d8885c936835ce59b87ac0587213ee17e914e6d5e9bd4aee
 size 1112252785

special_tokens_map.json

@@ -2,7 +2,13 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304364e2e8d0071c6a3c44ea4415d5704600003380d38fa4ed620433afe7e82e
-size 17082993
+oid sha256:affcfb1f45c4b14a70a6589c3d153b430ed4309e5a6613a88dab64d5a923a5d6
+size 17082925

tokenizer_config.json

@@ -2,9 +2,7 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": false,
   "eos_token": "</s>",
-  "full_tokenizer_file": null,
   "mask_token": {
     "__type": "AddedToken",
     "content": "<mask>",
@@ -13,17 +11,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "max_length": 256,
+  "max_length": 512,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "stride": 128,
+  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
   "truncation_side": "right",
-  "truncation_strategy": "only_second",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }