Upload 11 files

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<<ENT>>": 128002,
+  "<<SEP>>": 128003,
+  "[FLERT]": 128001,
+  "[MASK]": 128000
+}

gliner_config.json

@@ -0,0 +1,124 @@
+{
+  "class_token_index": 128002,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "microsoft/deberta-v3-small",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_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_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-07,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "min_length": 0,
+    "model_type": "deberta-v2",
+    "no_repeat_ngram_size": 0,
+    "norm_rel_ebd": "layer_norm",
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 6,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": 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,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "share_att_key": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 0,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 128004
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 5000,
+  "fine_tune": true,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 512,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "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/deberta-v3-small",
+  "model_type": "gliner",
+  "name": "correct",
+  "num_post_fusion_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": "4.44.2",
+  "vocab_size": 128004,
+  "warmup_ratio": 3000,
+  "words_splitter_type": "whitespace"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fb5f813a87f70c90bd2fd20705a6d88fa51ef0a553e1583b8a7fa5651c9382
+size 1221297210

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917a4ffca5cbbae5efb9e94a153c29cfb1c2cf066b1caabcff61f7bf9228727d
+size 610640046

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b6374a48b2dcfd4c9e837f0c6aaeb45e20322318b72bcab23c34ea9566836b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9846c4989506f12265964c3ab980b850152c6c261da42dda407343366a0fee62
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,82 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "[FLERT]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128002": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.151515151515152,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 1735.82958984375,
+      "learning_rate": 6.02409638554217e-06,
+      "loss": 178.0369,
+      "step": 50
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_loss": 141.81396484375,
+      "eval_runtime": 0.68,
+      "eval_samples_per_second": 44.12,
+      "eval_steps_per_second": 5.883,
+      "step": 50
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 878.3958129882812,
+      "learning_rate": 9.77088948787062e-06,
+      "loss": 140.1058,
+      "step": 100
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "eval_loss": 125.39718627929688,
+      "eval_runtime": 0.6771,
+      "eval_samples_per_second": 44.308,
+      "eval_steps_per_second": 5.908,
+      "step": 100
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 1332.434326171875,
+      "learning_rate": 9.097035040431268e-06,
+      "loss": 114.4198,
+      "step": 150
+    },
+    {
+      "epoch": 4.545454545454545,
+      "eval_loss": 114.40504455566406,
+      "eval_runtime": 0.6721,
+      "eval_samples_per_second": 44.639,
+      "eval_steps_per_second": 5.952,
+      "step": 150
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 1204.0079345703125,
+      "learning_rate": 8.423180592991915e-06,
+      "loss": 105.3163,
+      "step": 200
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "eval_loss": 108.37521362304688,
+      "eval_runtime": 0.6767,
+      "eval_samples_per_second": 44.33,
+      "eval_steps_per_second": 5.911,
+      "step": 200
+    },
+    {
+      "epoch": 7.575757575757576,
+      "grad_norm": 1180.3629150390625,
+      "learning_rate": 7.749326145552561e-06,
+      "loss": 94.5081,
+      "step": 250
+    },
+    {
+      "epoch": 7.575757575757576,
+      "eval_loss": 113.66868591308594,
+      "eval_runtime": 0.6817,
+      "eval_samples_per_second": 44.009,
+      "eval_steps_per_second": 5.868,
+      "step": 250
+    },
+    {
+      "epoch": 9.090909090909092,
+      "grad_norm": 1183.9482421875,
+      "learning_rate": 7.0754716981132075e-06,
+      "loss": 83.6025,
+      "step": 300
+    },
+    {
+      "epoch": 9.090909090909092,
+      "eval_loss": 109.58412170410156,
+      "eval_runtime": 0.6798,
+      "eval_samples_per_second": 44.127,
+      "eval_steps_per_second": 5.884,
+      "step": 300
+    },
+    {
+      "epoch": 10.606060606060606,
+      "grad_norm": 1322.03515625,
+      "learning_rate": 6.401617250673855e-06,
+      "loss": 80.1657,
+      "step": 350
+    },
+    {
+      "epoch": 10.606060606060606,
+      "eval_loss": 106.66357421875,
+      "eval_runtime": 0.6829,
+      "eval_samples_per_second": 43.928,
+      "eval_steps_per_second": 5.857,
+      "step": 350
+    },
+    {
+      "epoch": 12.121212121212121,
+      "grad_norm": 1885.264404296875,
+      "learning_rate": 5.727762803234502e-06,
+      "loss": 73.8062,
+      "step": 400
+    },
+    {
+      "epoch": 12.121212121212121,
+      "eval_loss": 115.17276763916016,
+      "eval_runtime": 0.6809,
+      "eval_samples_per_second": 44.056,
+      "eval_steps_per_second": 5.874,
+      "step": 400
+    },
+    {
+      "epoch": 13.636363636363637,
+      "grad_norm": 869.5314331054688,
+      "learning_rate": 5.053908355795149e-06,
+      "loss": 68.8767,
+      "step": 450
+    },
+    {
+      "epoch": 13.636363636363637,
+      "eval_loss": 109.55915832519531,
+      "eval_runtime": 0.6804,
+      "eval_samples_per_second": 44.093,
+      "eval_steps_per_second": 5.879,
+      "step": 450
+    },
+    {
+      "epoch": 15.151515151515152,
+      "grad_norm": 1756.1275634765625,
+      "learning_rate": 4.380053908355795e-06,
+      "loss": 69.1187,
+      "step": 500
+    },
+    {
+      "epoch": 15.151515151515152,
+      "eval_loss": 111.99463653564453,
+      "eval_runtime": 0.6735,
+      "eval_samples_per_second": 44.543,
+      "eval_steps_per_second": 5.939,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 825,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}