Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-103104/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-103104/config.json

@@ -0,0 +1,35 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

checkpoint-103104/config_sentence_transformers.json

@@ -0,0 +1,11 @@
+{
+  "__version__": {
+    "pytorch": "2.14.0+cu130",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.17.0"
+  },
+  "activation_fn": "torch.nn.modules.linear.Identity",
+  "default_prompt_name": null,
+  "model_type": "CrossEncoder",
+  "prompts": {}
+}

checkpoint-103104/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108ca30490758bff4ce9c74c26b11fa230b36837b181b56c9277a21615389dbd
+size 470588492

checkpoint-103104/modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  }
+]

checkpoint-103104/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff24cd411a37370a305db450df02a02ec81f9eb64454acfbd9cbf228a1f175a
+size 941300107

checkpoint-103104/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087843d19d54d96f790b66f36b77ffe6f65c51f185d188bfaad4dc29b22733d9
+size 14645

checkpoint-103104/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ff02daac65601b782d1d73accb1c8c7da0bad0188db6c277eb7f2cbbc9b190
+size 1465

checkpoint-103104/sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "sequence-classification",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "logits"
+        }
+    },
+    "module_output_name": "scores"
+}

checkpoint-103104/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

checkpoint-103104/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-103104/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc37942a2b024d70818605c864fbf6f0adef51b8be1200df524de523029b027
+size 5585

config.json

@@ -0,0 +1,35 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,11 @@
+{
+  "__version__": {
+    "pytorch": "2.14.0+cu130",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.17.0"
+  },
+  "activation_fn": "torch.nn.modules.linear.Identity",
+  "default_prompt_name": null,
+  "model_type": "CrossEncoder",
+  "prompts": {}
+}

eval/CrossEncoderClassificationEvaluator_ce-val_results.csv

@@ -0,0 +1,3 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+1.0,51552,0.9963412070194216,0.3375684,0.9903832352519019,0.15013409,0.9861791987651322,0.994623268418549,0.999500331869223
+2.0,103104,0.9968681824263258,0.20284656,0.9917682773667099,0.19957852,0.9875653889031816,0.9960070920963487,0.9996460692260924

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108ca30490758bff4ce9c74c26b11fa230b36837b181b56c9277a21615389dbd
+size 470588492

modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "sequence-classification",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "logits"
+        }
+    },
+    "module_output_name": "scores"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}