mertunsal commited on Nov 20

Commit

603f9d5

•

1 Parent(s): 2910290

Add files using upload-large-folder tool

Browse files

Files changed (18) hide show

added_tokens.json +6 -0
checkpoint-50000/added_tokens.json +6 -0
checkpoint-50000/gliner_config.json +137 -0
checkpoint-50000/optimizer.pt +3 -0
checkpoint-50000/pytorch_model.bin +3 -0
checkpoint-50000/rng_state.pth +3 -0
checkpoint-50000/scheduler.pt +3 -0
checkpoint-50000/special_tokens_map.json +15 -0
checkpoint-50000/spm.model +3 -0
checkpoint-50000/tokenizer.json +0 -0
checkpoint-50000/tokenizer_config.json +82 -0
checkpoint-50000/trainer_state.json +378 -0
gliner_config.json +137 -0
pytorch_model.bin +3 -0
special_tokens_map.json +15 -0
spm.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +82 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "<<ENT>>": 128002,
+  "<<SEP>>": 128003,
+  "[FLERT]": 128001,
+  "[MASK]": 128000
+}

checkpoint-50000/added_tokens.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "<<ENT>>": 128002,
+  "<<SEP>>": 128003,
+  "[FLERT]": 128001,
+  "[MASK]": 128000
+}

checkpoint-50000/gliner_config.json ADDED Viewed

	@@ -0,0 +1,137 @@

+{
+  "class_token_index": 128002,
+  "dropout": 0.1,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "microsoft/deberta-v3-large",
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "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": 1024,
+    "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": 1000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 512,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "logs_final",
+  "loss_alpha": 0.75,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "5e-6",
+  "lr_others": "7e-6",
+  "max_len": 768,
+  "max_neg_type_ratio": 1,
+  "max_types": 30,
+  "max_width": 100,
+  "model_name": "microsoft/deberta-v3-large",
+  "model_type": "gliner",
+  "name": "token level gliner large",
+  "num_post_fusion_layers": 1,
+  "num_steps": 6000,
+  "post_fusion_schema": "",
+  "prev_path": "logs_large/model_120000",
+  "random_drop": true,
+  "root_dir": "gliner_logs",
+  "save_total_limit": 10,
+  "scheduler_type": "linear",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "token_level",
+  "subtoken_pooling": "first",
+  "train_batch_size": 8,
+  "train_data": "../../data/unie_ner1.json",
+  "transformers_version": "4.40.1",
+  "val_data_dir": "none",
+  "vocab_size": 128004,
+  "warmup_ratio": 0.1,
+  "weight_decay_encoder": 0.01,
+  "weight_decay_other": 0.01,
+  "words_splitter_type": "whitespace"
+}

checkpoint-50000/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:178b10ff487d539f22da3e22b777821c150988312b2b8af20a72f6075b53608e
+size 3522103130

checkpoint-50000/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cf40327e9588679e6e466222c630d2f5c5d04e1ca930d4bcd39a63b504b62431
+size 1761030542

checkpoint-50000/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5b9570935ca7da83e5536673b5f5deed8c68ca623a88697fb18aa7860e23d3
+size 14244

checkpoint-50000/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f36a451441eddf56b9329713039c0569241d2ce572e01e2fad79181b3102d2a8
+size 1064

checkpoint-50000/special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

checkpoint-50000/spm.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

checkpoint-50000/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-50000/tokenizer_config.json ADDED Viewed

	@@ -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"
+}

checkpoint-50000/trainer_state.json ADDED Viewed

	@@ -0,0 +1,378 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9792592882743493,
+  "eval_steps": 500,
+  "global_step": 50000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.9585185765486987e-05,
+      "grad_norm": 5018.7451171875,
+      "learning_rate": 9.792401096748923e-10,
+      "loss": 208.5257,
+      "step": 1
+    },
+    {
+      "epoch": 0.019585185765486984,
+      "grad_norm": 2883.36767578125,
+      "learning_rate": 9.792401096748923e-07,
+      "loss": 81.6631,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03917037153097397,
+      "grad_norm": 20.049026489257812,
+      "learning_rate": 1.9584802193497847e-06,
+      "loss": 31.971,
+      "step": 2000
+    },
+    {
+      "epoch": 0.05875555729646096,
+      "grad_norm": 208.86001586914062,
+      "learning_rate": 2.937720329024677e-06,
+      "loss": 44.682,
+      "step": 3000
+    },
+    {
+      "epoch": 0.07834074306194794,
+      "grad_norm": 0.09099026769399643,
+      "learning_rate": 3.916960438699569e-06,
+      "loss": 44.3843,
+      "step": 4000
+    },
+    {
+      "epoch": 0.09792592882743492,
+      "grad_norm": 0.4517519772052765,
+      "learning_rate": 4.896200548374462e-06,
+      "loss": 43.43,
+      "step": 5000
+    },
+    {
+      "epoch": 0.11751111459292192,
+      "grad_norm": 1966.388427734375,
+      "learning_rate": 4.902726699018563e-06,
+      "loss": 40.5555,
+      "step": 6000
+    },
+    {
+      "epoch": 0.1370963003584089,
+      "grad_norm": 0.3393819332122803,
+      "learning_rate": 4.793919874654539e-06,
+      "loss": 42.1143,
+      "step": 7000
+    },
+    {
+      "epoch": 0.15668148612389587,
+      "grad_norm": 0.3584004044532776,
+      "learning_rate": 4.6851130502905145e-06,
+      "loss": 38.5059,
+      "step": 8000
+    },
+    {
+      "epoch": 0.17626667188938286,
+      "grad_norm": 31621.654296875,
+      "learning_rate": 4.57630622592649e-06,
+      "loss": 40.2935,
+      "step": 9000
+    },
+    {
+      "epoch": 0.19585185765486984,
+      "grad_norm": 0.382893830537796,
+      "learning_rate": 4.467499401562466e-06,
+      "loss": 38.6624,
+      "step": 10000
+    },
+    {
+      "epoch": 0.21543704342035686,
+      "grad_norm": 17.776079177856445,
+      "learning_rate": 4.358692577198442e-06,
+      "loss": 40.7107,
+      "step": 11000
+    },
+    {
+      "epoch": 0.23502222918584384,
+      "grad_norm": 0.009184932336211205,
+      "learning_rate": 4.249885752834419e-06,
+      "loss": 39.2709,
+      "step": 12000
+    },
+    {
+      "epoch": 0.2546074149513308,
+      "grad_norm": 1247.213623046875,
+      "learning_rate": 4.141078928470394e-06,
+      "loss": 40.3339,
+      "step": 13000
+    },
+    {
+      "epoch": 0.2741926007168178,
+      "grad_norm": 0.3560226857662201,
+      "learning_rate": 4.03227210410637e-06,
+      "loss": 37.2834,
+      "step": 14000
+    },
+    {
+      "epoch": 0.2937777864823048,
+      "grad_norm": 0.24219802021980286,
+      "learning_rate": 3.923465279742345e-06,
+      "loss": 39.1311,
+      "step": 15000
+    },
+    {
+      "epoch": 0.31336297224779175,
+      "grad_norm": 0.2203676551580429,
+      "learning_rate": 3.8146584553783216e-06,
+      "loss": 39.8453,
+      "step": 16000
+    },
+    {
+      "epoch": 0.33294815801327876,
+      "grad_norm": 0.3494016230106354,
+      "learning_rate": 3.705851631014298e-06,
+      "loss": 41.8208,
+      "step": 17000
+    },
+    {
+      "epoch": 0.3525333437787657,
+      "grad_norm": 0.3340425491333008,
+      "learning_rate": 3.5970448066502733e-06,
+      "loss": 38.6235,
+      "step": 18000
+    },
+    {
+      "epoch": 0.37211852954425273,
+      "grad_norm": 242.7712860107422,
+      "learning_rate": 3.4882379822862495e-06,
+      "loss": 38.3089,
+      "step": 19000
+    },
+    {
+      "epoch": 0.3917037153097397,
+      "grad_norm": 124.58765411376953,
+      "learning_rate": 3.379431157922225e-06,
+      "loss": 38.0979,
+      "step": 20000
+    },
+    {
+      "epoch": 0.4112889010752267,
+      "grad_norm": 1757.1505126953125,
+      "learning_rate": 3.2706243335582012e-06,
+      "loss": 38.5866,
+      "step": 21000
+    },
+    {
+      "epoch": 0.4308740868407137,
+      "grad_norm": 0.12498880177736282,
+      "learning_rate": 3.161817509194177e-06,
+      "loss": 37.7957,
+      "step": 22000
+    },
+    {
+      "epoch": 0.45045927260620067,
+      "grad_norm": 0.5418808460235596,
+      "learning_rate": 3.053010684830153e-06,
+      "loss": 39.3742,
+      "step": 23000
+    },
+    {
+      "epoch": 0.4700444583716877,
+      "grad_norm": 786.1953735351562,
+      "learning_rate": 2.9442038604661287e-06,
+      "loss": 40.0331,
+      "step": 24000
+    },
+    {
+      "epoch": 0.48962964413717464,
+      "grad_norm": 0.4919143319129944,
+      "learning_rate": 2.8353970361021046e-06,
+      "loss": 34.2143,
+      "step": 25000
+    },
+    {
+      "epoch": 0.5092148299026616,
+      "grad_norm": 0.18596726655960083,
+      "learning_rate": 2.7265902117380804e-06,
+      "loss": 41.537,
+      "step": 26000
+    },
+    {
+      "epoch": 0.5288000156681486,
+      "grad_norm": 0.4064764380455017,
+      "learning_rate": 2.6177833873740567e-06,
+      "loss": 32.8328,
+      "step": 27000
+    },
+    {
+      "epoch": 0.5483852014336356,
+      "grad_norm": 0.15870028734207153,
+      "learning_rate": 2.508976563010032e-06,
+      "loss": 37.4091,
+      "step": 28000
+    },
+    {
+      "epoch": 0.5679703871991226,
+      "grad_norm": 1464.27099609375,
+      "learning_rate": 2.400169738646008e-06,
+      "loss": 37.2837,
+      "step": 29000
+    },
+    {
+      "epoch": 0.5875555729646096,
+      "grad_norm": 0.3748704791069031,
+      "learning_rate": 2.291362914281984e-06,
+      "loss": 37.0786,
+      "step": 30000
+    },
+    {
+      "epoch": 0.6071407587300965,
+      "grad_norm": 0.3047567903995514,
+      "learning_rate": 2.18255608991796e-06,
+      "loss": 35.8922,
+      "step": 31000
+    },
+    {
+      "epoch": 0.6267259444955835,
+      "grad_norm": 881.1626586914062,
+      "learning_rate": 2.073749265553936e-06,
+      "loss": 35.0494,
+      "step": 32000
+    },
+    {
+      "epoch": 0.6463111302610706,
+      "grad_norm": 0.34886327385902405,
+      "learning_rate": 1.9649424411899117e-06,
+      "loss": 39.6155,
+      "step": 33000
+    },
+    {
+      "epoch": 0.6658963160265575,
+      "grad_norm": 0.4310557544231415,
+      "learning_rate": 1.8561356168258875e-06,
+      "loss": 38.9501,
+      "step": 34000
+    },
+    {
+      "epoch": 0.6854815017920445,
+      "grad_norm": 337.7919616699219,
+      "learning_rate": 1.7473287924618634e-06,
+      "loss": 35.0407,
+      "step": 35000
+    },
+    {
+      "epoch": 0.7050666875575314,
+      "grad_norm": 1063.1663818359375,
+      "learning_rate": 1.6385219680978392e-06,
+      "loss": 36.926,
+      "step": 36000
+    },
+    {
+      "epoch": 0.7246518733230185,
+      "grad_norm": 112.55769348144531,
+      "learning_rate": 1.529715143733815e-06,
+      "loss": 36.4123,
+      "step": 37000
+    },
+    {
+      "epoch": 0.7442370590885055,
+      "grad_norm": 0.43231236934661865,
+      "learning_rate": 1.4209083193697909e-06,
+      "loss": 32.0216,
+      "step": 38000
+    },
+    {
+      "epoch": 0.7638222448539924,
+      "grad_norm": 0.27660930156707764,
+      "learning_rate": 1.312101495005767e-06,
+      "loss": 32.359,
+      "step": 39000
+    },
+    {
+      "epoch": 0.7834074306194794,
+      "grad_norm": 0.28697681427001953,
+      "learning_rate": 1.2032946706417428e-06,
+      "loss": 37.6499,
+      "step": 40000
+    },
+    {
+      "epoch": 0.8029926163849664,
+      "grad_norm": 0.18463213741779327,
+      "learning_rate": 1.0944878462777186e-06,
+      "loss": 34.4977,
+      "step": 41000
+    },
+    {
+      "epoch": 0.8225778021504534,
+      "grad_norm": 110.25094604492188,
+      "learning_rate": 9.856810219136945e-07,
+      "loss": 37.8532,
+      "step": 42000
+    },
+    {
+      "epoch": 0.8421629879159404,
+      "grad_norm": 0.3026086091995239,
+      "learning_rate": 8.768741975496704e-07,
+      "loss": 35.3672,
+      "step": 43000
+    },
+    {
+      "epoch": 0.8617481736814274,
+      "grad_norm": 0.3170241713523865,
+      "learning_rate": 7.680673731856462e-07,
+      "loss": 38.3382,
+      "step": 44000
+    },
+    {
+      "epoch": 0.8813333594469144,
+      "grad_norm": 768.84716796875,
+      "learning_rate": 6.592605488216222e-07,
+      "loss": 35.3662,
+      "step": 45000
+    },
+    {
+      "epoch": 0.9009185452124013,
+      "grad_norm": 0.4777417778968811,
+      "learning_rate": 5.50453724457598e-07,
+      "loss": 41.6652,
+      "step": 46000
+    },
+    {
+      "epoch": 0.9205037309778883,
+      "grad_norm": 0.32603392004966736,
+      "learning_rate": 4.416469000935739e-07,
+      "loss": 40.3125,
+      "step": 47000
+    },
+    {
+      "epoch": 0.9400889167433754,
+      "grad_norm": 0.3190682530403137,
+      "learning_rate": 3.3284007572954976e-07,
+      "loss": 36.4948,
+      "step": 48000
+    },
+    {
+      "epoch": 0.9596741025088623,
+      "grad_norm": 0.2428392767906189,
+      "learning_rate": 2.2403325136552568e-07,
+      "loss": 37.7761,
+      "step": 49000
+    },
+    {
+      "epoch": 0.9792592882743493,
+      "grad_norm": 3454.626220703125,
+      "learning_rate": 1.1522642700150154e-07,
+      "loss": 38.9872,
+      "step": 50000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 51059,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

gliner_config.json ADDED Viewed

	@@ -0,0 +1,137 @@

+{
+  "class_token_index": 128002,
+  "dropout": 0.1,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "microsoft/deberta-v3-large",
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "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": 1024,
+    "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": 1000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 512,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "logs_final",
+  "loss_alpha": 0.75,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "5e-6",
+  "lr_others": "7e-6",
+  "max_len": 768,
+  "max_neg_type_ratio": 1,
+  "max_types": 30,
+  "max_width": 100,
+  "model_name": "microsoft/deberta-v3-large",
+  "model_type": "gliner",
+  "name": "token level gliner large",
+  "num_post_fusion_layers": 1,
+  "num_steps": 6000,
+  "post_fusion_schema": "",
+  "prev_path": "logs_large/model_120000",
+  "random_drop": true,
+  "root_dir": "gliner_logs",
+  "save_total_limit": 10,
+  "scheduler_type": "linear",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "token_level",
+  "subtoken_pooling": "first",
+  "train_batch_size": 8,
+  "train_data": "../../data/unie_ner1.json",
+  "transformers_version": "4.40.1",
+  "val_data_dir": "none",
+  "vocab_size": 128004,
+  "warmup_ratio": 0.1,
+  "weight_decay_encoder": 0.01,
+  "weight_decay_other": 0.01,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:17f36aa9cf90424f0264adc51b92b803ce52186c9f90384a677700d924af2845
+size 1761030542

special_tokens_map.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -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"
+}