Upload 11 files

.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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+    "[MASK]": 128000
+}

gliner_config.json

@@ -0,0 +1,216 @@
+{
+    "class_token_index": -1,
+    "dropout": 0.3,
+    "embed_ent_token": true,
+    "encoder_config": {
+        "_name_or_path": "microsoft/deberta-v3-base",
+        "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,
+        "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-7,
+        "length_penalty": 1,
+        "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": 12,
+        "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,
+        "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,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1,
+        "torch_dtype": null,
+        "torchscript": false,
+        "type_vocab_size": 0,
+        "typical_p": 1,
+        "use_bfloat16": false,
+        "vocab_size": 128100
+    },
+    "ent_token": "<<ENT>>",
+    "eval_every": 5000,
+    "fine_tune": true,
+    "freeze_token_rep": false,
+    "fuse_layers": false,
+    "has_rnn": true,
+    "hidden_size": 768,
+    "label_smoothing": 0,
+    "labels_encoder": "BAAI/bge-small-en-v1.5",
+    "labels_encoder_config": {
+        "_name_or_path": "BAAI/bge-small-en-v1.5",
+        "add_cross_attention": false,
+        "architectures": [
+            "BertModel"
+        ],
+        "attention_probs_dropout_prob": 0.1,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "classifier_dropout": null,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 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": 384,
+        "id2label": {
+            "0": "LABEL_0"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 1536,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0
+        },
+        "layer_norm_eps": 1e-12,
+        "length_penalty": 1,
+        "max_length": 20,
+        "max_position_embeddings": 512,
+        "min_length": 0,
+        "model_type": "bert",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 12,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_hidden_layers": 12,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": 0,
+        "position_embedding_type": "absolute",
+        "prefix": null,
+        "problem_type": null,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "sep_token_id": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1,
+        "torch_dtype": "float32",
+        "torchscript": false,
+        "type_vocab_size": 2,
+        "typical_p": 1,
+        "use_bfloat16": false,
+        "use_cache": true,
+        "vocab_size": 30522
+    },
+    "log_dir": "deberta/",
+    "loss_alpha": 0.8,
+    "loss_gamma": 2,
+    "loss_reduction": "sum",
+    "lr_encoder": "1e-5",
+    "lr_others": "5e-5",
+    "max_grad_norm": 10,
+    "max_len": 512,
+    "max_neg_type_ratio": 1,
+    "max_types": 100,
+    "max_width": 12,
+    "model_name": "microsoft/deberta-v3-base",
+    "model_type": "gliner",
+    "name": "span level gliner",
+    "num_post_fusion_layers": 1,
+    "num_steps": 100000,
+    "post_fusion_schema": "",
+    "prev_path": null,
+    "random_drop": true,
+    "root_dir": "gliner_logs",
+    "save_total_limit": 3,
+    "scheduler_type": "cosine",
+    "sep_token": "<<SEP>>",
+    "shuffle_types": true,
+    "size_sup": -1,
+    "span_mode": "markerV0",
+    "subtoken_pooling": "first",
+    "train_batch_size": 8,
+    "train_data": "data/nuner_train.json",
+    "transformers_version": "4.45.2",
+    "val_data_dir": "none",
+    "vocab_size": -1,
+    "warmup_ratio": 0.05,
+    "weight_decay_encoder": 0.1,
+    "weight_decay_other": 0.1,
+    "words_splitter_type": "whitespace"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed884e4c7dfd04f844f34450ae3dea9fa4dde54141913f2e58b8237988643aa0
+size 1909053417

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b05009068f723953cd2a19492413f0842554ace11fa073b7996c6ded005136f
+size 969281034

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b36b09dc0d742cdacb85dd59355e8b0ba4e300d7b51f6f0b3f8c4b0262325d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1828686b8230c9d213a7809ad8e1222b72b42341bfd713e543489ff5454fd5
+size 1064

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:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335e95775c824ea2e442870aa5454366947f1d99fa433870300fec9cd5b62846
+size 12745761

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+    "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
+        }
+    },
+    "bos_token": "[CLS]",
+    "clean_up_tokenization_spaces": true,
+    "cls_token": "[CLS]",
+    "do_lower_case": false,
+    "eos_token": "[SEP]",
+    "mask_token": "[MASK]",
+    "model_max_length": 1e+30,
+    "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 +1,303 @@
+{
+    "best_metric": null,
+    "best_model_checkpoint": null,
+    "epoch": 3.568065810991625,
+    "eval_steps": 500,
+    "global_step": 9000,
+    "is_hyper_param_search": false,
+    "is_local_process_zero": true,
+    "is_world_process_zero": true,
+    "log_history": [
+        {
+            "epoch": 0.19822587838842362,
+            "grad_norm": 47.1356201171875,
+            "learning_rate": 0.0000024777006937561945,
+            "loss": 21.4029,
+            "step": 500
+        },
+        {
+            "epoch": 0.19822587838842362,
+            "eval_loss": 586.7496948242188,
+            "eval_runtime": 573.4198,
+            "eval_samples_per_second": 53,
+            "eval_steps_per_second": 6.625,
+            "step": 500
+        },
+        {
+            "epoch": 0.39645175677684724,
+            "grad_norm": 50.89448165893555,
+            "learning_rate": 0.000004955401387512389,
+            "loss": 11.7925,
+            "step": 1000
+        },
+        {
+            "epoch": 0.39645175677684724,
+            "eval_loss": 584.6571044921875,
+            "eval_runtime": 571.5589,
+            "eval_samples_per_second": 53.172,
+            "eval_steps_per_second": 6.647,
+            "step": 1000
+        },
+        {
+            "epoch": 0.5946776351652708,
+            "grad_norm": 56.098140716552734,
+            "learning_rate": 0.000007433102081268584,
+            "loss": 9.7243,
+            "step": 1500
+        },
+        {
+            "epoch": 0.5946776351652708,
+            "eval_loss": 438.975830078125,
+            "eval_runtime": 571.006,
+            "eval_samples_per_second": 53.224,
+            "eval_steps_per_second": 6.653,
+            "step": 1500
+        },
+        {
+            "epoch": 0.7929035135536945,
+            "grad_norm": 49.88700485229492,
+            "learning_rate": 0.000009910802775024778,
+            "loss": 8.6629,
+            "step": 2000
+        },
+        {
+            "epoch": 0.7929035135536945,
+            "eval_loss": 443.8860778808594,
+            "eval_runtime": 569.8536,
+            "eval_samples_per_second": 53.331,
+            "eval_steps_per_second": 6.667,
+            "step": 2000
+        },
+        {
+            "epoch": 0.991129391942118,
+            "grad_norm": 37.3896484375,
+            "learning_rate": 0.00000991223686038578,
+            "loss": 7.7527,
+            "step": 2500
+        },
+        {
+            "epoch": 0.991129391942118,
+            "eval_loss": 359.1586608886719,
+            "eval_runtime": 570.3107,
+            "eval_samples_per_second": 53.289,
+            "eval_steps_per_second": 6.661,
+            "step": 2500
+        },
+        {
+            "epoch": 1.1893552703305417,
+            "grad_norm": 45.05537414550781,
+            "learning_rate": 0.000009639072360499928,
+            "loss": 7.0532,
+            "step": 3000
+        },
+        {
+            "epoch": 1.1893552703305417,
+            "eval_loss": 297.4908447265625,
+            "eval_runtime": 573.7765,
+            "eval_samples_per_second": 52.967,
+            "eval_steps_per_second": 6.621,
+            "step": 3000
+        },
+        {
+            "epoch": 1.3875811487189653,
+            "grad_norm": 42.01622772216797,
+            "learning_rate": 0.000009190700553732768,
+            "loss": 6.8798,
+            "step": 3500
+        },
+        {
+            "epoch": 1.3875811487189653,
+            "eval_loss": 272.1216125488281,
+            "eval_runtime": 570.5906,
+            "eval_samples_per_second": 53.262,
+            "eval_steps_per_second": 6.658,
+            "step": 3500
+        },
+        {
+            "epoch": 1.5858070271073887,
+            "grad_norm": 26.336191177368164,
+            "learning_rate": 0.000008584055432624292,
+            "loss": 6.5736,
+            "step": 4000
+        },
+        {
+            "epoch": 1.5858070271073887,
+            "eval_loss": 279.0899353027344,
+            "eval_runtime": 578.6986,
+            "eval_samples_per_second": 52.516,
+            "eval_steps_per_second": 6.565,
+            "step": 4000
+        },
+        {
+            "epoch": 1.7840329054958124,
+            "grad_norm": 35.772953033447266,
+            "learning_rate": 0.00000784204861605915,
+            "loss": 6.3985,
+            "step": 4500
+        },
+        {
+            "epoch": 1.7840329054958124,
+            "eval_loss": 221.53627014160156,
+            "eval_runtime": 569.7883,
+            "eval_samples_per_second": 53.337,
+            "eval_steps_per_second": 6.667,
+            "step": 4500
+        },
+        {
+            "epoch": 1.982258783884236,
+            "grad_norm": 34.2270622253418,
+            "learning_rate": 0.000006992704029062722,
+            "loss": 6.0866,
+            "step": 5000
+        },
+        {
+            "epoch": 1.982258783884236,
+            "eval_loss": 190.98533630371094,
+            "eval_runtime": 571.0123,
+            "eval_samples_per_second": 53.223,
+            "eval_steps_per_second": 6.653,
+            "step": 5000
+        },
+        {
+            "epoch": 2.1804846622726597,
+            "grad_norm": 34.992889404296875,
+            "learning_rate": 0.000006068099502317051,
+            "loss": 5.732,
+            "step": 5500
+        },
+        {
+            "epoch": 2.1804846622726597,
+            "eval_loss": 225.56539916992188,
+            "eval_runtime": 570.6646,
+            "eval_samples_per_second": 53.255,
+            "eval_steps_per_second": 6.657,
+            "step": 5500
+        },
+        {
+            "epoch": 2.3787105406610833,
+            "grad_norm": 35.05290222167969,
+            "learning_rate": 0.000005103155264797376,
+            "loss": 5.8384,
+            "step": 6000
+        },
+        {
+            "epoch": 2.3787105406610833,
+            "eval_loss": 206.36277770996094,
+            "eval_runtime": 569.1115,
+            "eval_samples_per_second": 53.401,
+            "eval_steps_per_second": 6.675,
+            "step": 6000
+        },
+        {
+            "epoch": 2.576936419049507,
+            "grad_norm": 38.268341064453125,
+            "learning_rate": 0.0000041343150854317275,
+            "loss": 5.6189,
+            "step": 6500
+        },
+        {
+            "epoch": 2.576936419049507,
+            "eval_loss": 211.91796875,
+            "eval_runtime": 569.7007,
+            "eval_samples_per_second": 53.346,
+            "eval_steps_per_second": 6.668,
+            "step": 6500
+        },
+        {
+            "epoch": 2.7751622974379306,
+            "grad_norm": 42.83818054199219,
+            "learning_rate": 0.0000031981698740904465,
+            "loss": 5.5445,
+            "step": 7000
+        },
+        {
+            "epoch": 2.7751622974379306,
+            "eval_loss": 199.4452362060547,
+            "eval_runtime": 570.9073,
+            "eval_samples_per_second": 53.233,
+            "eval_steps_per_second": 6.654,
+            "step": 7000
+        },
+        {
+            "epoch": 2.9733881758263543,
+            "grad_norm": 42.24338150024414,
+            "learning_rate": 0.0000023300757253939837,
+            "loss": 5.546,
+            "step": 7500
+        },
+        {
+            "epoch": 2.9733881758263543,
+            "eval_loss": 190.01214599609375,
+            "eval_runtime": 571.9686,
+            "eval_samples_per_second": 53.134,
+            "eval_steps_per_second": 6.642,
+            "step": 7500
+        },
+        {
+            "epoch": 3.171614054214778,
+            "grad_norm": 34.228065490722656,
+            "learning_rate": 0.0000015628185987094685,
+            "loss": 5.3668,
+            "step": 8000
+        },
+        {
+            "epoch": 3.171614054214778,
+            "eval_loss": 194.59649658203125,
+            "eval_runtime": 571.773,
+            "eval_samples_per_second": 53.152,
+            "eval_steps_per_second": 6.644,
+            "step": 8000
+        },
+        {
+            "epoch": 3.3698399326032016,
+            "grad_norm": 30.128808975219727,
+            "learning_rate": 9.253760663628896e-7,
+            "loss": 5.338,
+            "step": 8500
+        },
+        {
+            "epoch": 3.3698399326032016,
+            "eval_loss": 173.66778564453125,
+            "eval_runtime": 569.7472,
+            "eval_samples_per_second": 53.341,
+            "eval_steps_per_second": 6.668,
+            "step": 8500
+        },
+        {
+            "epoch": 3.568065810991625,
+            "grad_norm": 54.32496643066406,
+            "learning_rate": 4.4182289604595254e-7,
+            "loss": 5.2961,
+            "step": 9000
+        },
+        {
+            "epoch": 3.568065810991625,
+            "eval_loss": 184.6847381591797,
+            "eval_runtime": 571.6945,
+            "eval_samples_per_second": 53.16,
+            "eval_steps_per_second": 6.645,
+            "step": 9000
+        }
+    ],
+    "logging_steps": 500,
+    "max_steps": 10088,
+    "num_input_tokens_seen": 0,
+    "num_train_epochs": 4,
+    "save_steps": 1000,
+    "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,
+    "train_batch_size": 8,
+    "trial_name": null,
+    "trial_params": null
+}