Training in progress, step 7277

config.json

@@ -1,34 +1,32 @@
 {
-  "_name_or_path": "BAAI/bge-reranker-v2-m3",
+  "_name_or_path": "intfloat/multilingual-e5-small",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 384,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 1536,
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 8194,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 1,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 250037
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ac8a4b37d08fc34fdc404d09c9107f5fca94d2ac73640f79f5efc0201b50ad
-size 2271071852
+oid sha256:e7782e2ad309bf78bb6b772dc82e28bbec26edaad16329d90b6c0710ec21097b
+size 470640124

special_tokens_map.json

@@ -22,7 +22,7 @@
   },
   "mask_token": {
     "content": "<mask>",
-    "lstrip": true,
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false

tokenizer_config.json

@@ -34,7 +34,7 @@
     },
     "250001": {
       "content": "<mask>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
@@ -46,7 +46,7 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 8192,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30aa8e177ab8d7de826f71cdbfa3a0b85ab7ee187a22521f5955d4fd34f35fe
+oid sha256:66c936ff32fd4d9dd2cce2191fdf707c4e4fad7601d38f5f2f1d16840a07c58a
 size 5176