Training in progress, step 3000

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<<ENT>>": 96872,
+  "<<SEP>>": 96873,
+  "[CLS]": 96871,
+  "[MASK]": 96867,
+  "[PAD]": 96869,
+  "[SEP]": 96868,
+  "[UNK]": 96870
+}

gliner_config.json

@@ -0,0 +1,46 @@
+{
+  "class_token_index": 96872,
+  "dropout": 0.4,
+  "encoder_config": null,
+  "ent_token": "<<ENT>>",
+  "eval_every": 500,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "has_rnn": true,
+  "hidden_size": 768,
+  "label_smoothing": 0,
+  "log_dir": "ner-jp-gliner",
+  "loss_alpha": -1,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_grad_norm": 1.0,
+  "max_len": 384,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 12,
+  "model_name": "ku-nlp/deberta-v3-base-japanese",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_steps": 1000,
+  "prev_path": "none",
+  "random_drop": true,
+  "root_dir": "gliner_logs",
+  "save_total_limit": 10,
+  "scheduler_type": "cosine",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "markerV0",
+  "subtoken_pooling": "first",
+  "train_batch_size": 8,
+  "train_data": "ner_jp.json",
+  "transformers_version": "4.41.2",
+  "val_data_dir": "none",
+  "vocab_size": 96874,
+  "warmup_ratio": 0.1,
+  "weight_decay_encoder": 0.01,
+  "weight_decay_other": 0.01,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5eada49a4a048d5cd679921a5f21af9be1414ad3c4e77a2ebca5e4659d44139
+size 738656806

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fefde905766244f5e613a490d6e35236043d6483c4aae0eaac4b4a8fc365a88
+size 1658609

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "added_tokens_decoder": {
+    "96867": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96868": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96869": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96870": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96871": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96872": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96873": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f40347224bd5f89ab684db9e3b05d3e2c88ee05805357db27ab220b08a6b62e
+size 5304