Best eval loss: 11.030856132507324

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

gliner_config.json

@@ -0,0 +1,84 @@
+{
+  "class_token_index": 250103,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "microsoft/mdeberta-v3-base",
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "dtype": null,
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-07,
+    "legacy": true,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "model_type": "deberta-v2",
+    "norm_rel_ebd": "layer_norm",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "pooler_dropout": 0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 768,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": false,
+    "position_buckets": 256,
+    "problem_type": null,
+    "relative_attention": true,
+    "return_dict": true,
+    "share_att_key": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 0,
+    "vocab_size": 250105
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 5000,
+  "fine_tune": true,
+  "fuse_layers": false,
+  "hidden_size": 512,
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_len": 384,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 12,
+  "model_name": "microsoft/mdeberta-v3-base",
+  "model_type": null,
+  "name": "correct",
+  "num_post_fusion_layers": 1,
+  "num_rnn_layers": 1,
+  "num_steps": 30000,
+  "post_fusion_schema": "",
+  "random_drop": true,
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "markerV0",
+  "subtoken_pooling": "first",
+  "train_batch_size": 8,
+  "transformers_version": "5.0.0",
+  "vocab_size": 250105,
+  "warmup_ratio": 3000,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be82b511247f455360b6eb09034c60f4ed12ce8321bb44b3edfee9d70b3be420
+size 1155877731

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878c7e496f4dfdb03194ba7ba49b67b5092da20221c41c8a3887e5bc07b76183
+size 16033785

tokenizer_config.json

@@ -0,0 +1,123 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]",
+    "▁<extra_id_99>",
+    "▁<extra_id_98>",
+    "▁<extra_id_97>",
+    "▁<extra_id_96>",
+    "▁<extra_id_95>",
+    "▁<extra_id_94>",
+    "▁<extra_id_93>",
+    "▁<extra_id_92>",
+    "▁<extra_id_91>",
+    "▁<extra_id_90>",
+    "▁<extra_id_89>",
+    "▁<extra_id_88>",
+    "▁<extra_id_87>",
+    "▁<extra_id_86>",
+    "▁<extra_id_85>",
+    "▁<extra_id_84>",
+    "▁<extra_id_83>",
+    "▁<extra_id_82>",
+    "▁<extra_id_81>",
+    "▁<extra_id_80>",
+    "▁<extra_id_79>",
+    "▁<extra_id_78>",
+    "▁<extra_id_77>",
+    "▁<extra_id_76>",
+    "▁<extra_id_75>",
+    "▁<extra_id_74>",
+    "▁<extra_id_73>",
+    "▁<extra_id_72>",
+    "▁<extra_id_71>",
+    "▁<extra_id_70>",
+    "▁<extra_id_69>",
+    "▁<extra_id_68>",
+    "▁<extra_id_67>",
+    "▁<extra_id_66>",
+    "▁<extra_id_65>",
+    "▁<extra_id_64>",
+    "▁<extra_id_63>",
+    "▁<extra_id_62>",
+    "▁<extra_id_61>",
+    "▁<extra_id_60>",
+    "▁<extra_id_59>",
+    "▁<extra_id_58>",
+    "▁<extra_id_57>",
+    "▁<extra_id_56>",
+    "▁<extra_id_55>",
+    "▁<extra_id_54>",
+    "▁<extra_id_53>",
+    "▁<extra_id_52>",
+    "▁<extra_id_51>",
+    "▁<extra_id_50>",
+    "▁<extra_id_49>",
+    "▁<extra_id_48>",
+    "▁<extra_id_47>",
+    "▁<extra_id_46>",
+    "▁<extra_id_45>",
+    "▁<extra_id_44>",
+    "▁<extra_id_43>",
+    "▁<extra_id_42>",
+    "▁<extra_id_41>",
+    "▁<extra_id_40>",
+    "▁<extra_id_39>",
+    "▁<extra_id_38>",
+    "▁<extra_id_37>",
+    "▁<extra_id_36>",
+    "▁<extra_id_35>",
+    "▁<extra_id_34>",
+    "▁<extra_id_33>",
+    "▁<extra_id_32>",
+    "▁<extra_id_31>",
+    "▁<extra_id_30>",
+    "▁<extra_id_29>",
+    "▁<extra_id_28>",
+    "▁<extra_id_27>",
+    "▁<extra_id_26>",
+    "▁<extra_id_25>",
+    "▁<extra_id_24>",
+    "▁<extra_id_23>",
+    "▁<extra_id_22>",
+    "▁<extra_id_21>",
+    "▁<extra_id_20>",
+    "▁<extra_id_19>",
+    "▁<extra_id_18>",
+    "▁<extra_id_17>",
+    "▁<extra_id_16>",
+    "▁<extra_id_15>",
+    "▁<extra_id_14>",
+    "▁<extra_id_13>",
+    "▁<extra_id_12>",
+    "▁<extra_id_11>",
+    "▁<extra_id_10>",
+    "▁<extra_id_9>",
+    "▁<extra_id_8>",
+    "▁<extra_id_7>",
+    "▁<extra_id_6>",
+    "▁<extra_id_5>",
+    "▁<extra_id_4>",
+    "▁<extra_id_3>",
+    "▁<extra_id_2>",
+    "▁<extra_id_1>",
+    "▁<extra_id_0>"
+  ],
+  "is_local": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}