Upload folder using huggingface_hub

.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 +1,4 @@
+{
+  "<<ENT>>": 250002,
+  "<<SEP>>": 250003
+}

gliner_config.json

@@ -0,0 +1,133 @@
+{
+  "class_token_index": 250002,
+  "dropout": 0.4,
+  "embed_ent_token": false,
+  "encoder_config": {
+    "_name_or_path": "BAAI/bge-m3",
+    "add_cross_attention": false,
+    "architectures": [
+      "XLMRobertaModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "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": 2,
+    "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-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 8194,
+    "min_length": 0,
+    "model_type": "xlm-roberta",
+    "no_repeat_ngram_size": 0,
+    "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_past": true,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "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": "float32",
+    "torchscript": false,
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 250004
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 1000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_post_transformer": false,
+  "has_rnn": true,
+  "hidden_size": 1024,
+  "label_smoothing": 0.0001,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "models/bge",
+  "loss_alpha": 0.75,
+  "loss_gamma": 2,
+  "loss_reduction": "sum",
+  "lr_encoder": "9e-6",
+  "lr_others": "5e-5",
+  "max_grad_norm": 10.0,
+  "max_len": 1024,
+  "max_neg_type_ratio": 1,
+  "max_types": 100,
+  "max_width": 12,
+  "model_name": "BAAI/bge-m3",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 3,
+  "num_steps": 7000,
+  "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.json",
+  "transformers_version": "4.44.2",
+  "val_data_dir": "none",
+  "vocab_size": 250004,
+  "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 sha256:38134a6bf15585c59cd1ce071cd8cc8250ce62b3414b0a288389a47c0a91f8ff
+size 2447480898

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2549b7f6b8aaab038d4ea738d184047cbfcadf79ca5338002271d6f71e9b5fb5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bda6f92f0b9fc0f890a0e800611e258e3cd720628ed421795a016d87c60511
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f5bbe43ebfcb76fd3ea0e1222d7632b3bb148c67ba976b75e95610dea6fb25
+size 17083167

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.584507042253521,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0880281690140845,
+      "grad_norm": 1221.827392578125,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 297.1973,
+      "step": 100
+    },
+    {
+      "epoch": 0.176056338028169,
+      "grad_norm": 1063.7159423828125,
+      "learning_rate": 4.998119881260576e-06,
+      "loss": 161.9498,
+      "step": 200
+    },
+    {
+      "epoch": 0.2640845070422535,
+      "grad_norm": 1415.1790771484375,
+      "learning_rate": 4.93261217644956e-06,
+      "loss": 149.2985,
+      "step": 300
+    },
+    {
+      "epoch": 0.352112676056338,
+      "grad_norm": 1143.650634765625,
+      "learning_rate": 4.775907352415367e-06,
+      "loss": 146.5141,
+      "step": 400
+    },
+    {
+      "epoch": 0.44014084507042256,
+      "grad_norm": 1112.0836181640625,
+      "learning_rate": 4.533880175657419e-06,
+      "loss": 125.0505,
+      "step": 500
+    },
+    {
+      "epoch": 0.528169014084507,
+      "grad_norm": 2647.099365234375,
+      "learning_rate": 4.215604094671835e-06,
+      "loss": 136.0549,
+      "step": 600
+    },
+    {
+      "epoch": 0.6161971830985915,
+      "grad_norm": 914.672119140625,
+      "learning_rate": 3.833011082004229e-06,
+      "loss": 152.9934,
+      "step": 700
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 941.3635864257812,
+      "learning_rate": 3.400444312011776e-06,
+      "loss": 142.6481,
+      "step": 800
+    },
+    {
+      "epoch": 0.7922535211267606,
+      "grad_norm": 2750.364990234375,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 180.6238,
+      "step": 900
+    },
+    {
+      "epoch": 0.8802816901408451,
+      "grad_norm": 1102.6456298828125,
+      "learning_rate": 2.4515216705704396e-06,
+      "loss": 160.7811,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9683098591549296,
+      "grad_norm": 2127.451416015625,
+      "learning_rate": 1.970740319426474e-06,
+      "loss": 136.9254,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 415.93927001953125,
+      "eval_runtime": 8.7817,
+      "eval_samples_per_second": 115.012,
+      "eval_steps_per_second": 14.462,
+      "step": 1136
+    },
+    {
+      "epoch": 1.056338028169014,
+      "grad_norm": 2116.73193359375,
+      "learning_rate": 1.509800584902108e-06,
+      "loss": 142.92,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1443661971830985,
+      "grad_norm": 1667.754638671875,
+      "learning_rate": 1.085982811283654e-06,
+      "loss": 141.8554,
+      "step": 1300
+    },
+    {
+      "epoch": 1.232394366197183,
+      "grad_norm": 1366.0006103515625,
+      "learning_rate": 7.151756636052529e-07,
+      "loss": 149.8122,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3204225352112675,
+      "grad_norm": 1805.1434326171875,
+      "learning_rate": 4.1128047146765936e-07,
+      "loss": 148.2215,
+      "step": 1500
+    },
+    {
+      "epoch": 1.408450704225352,
+      "grad_norm": 1603.68212890625,
+      "learning_rate": 1.8569007682777417e-07,
+      "loss": 142.1948,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4964788732394365,
+      "grad_norm": 1250.8704833984375,
+      "learning_rate": 4.6861723431538273e-08,
+      "loss": 123.6116,
+      "step": 1700
+    },
+    {
+      "epoch": 1.584507042253521,
+      "grad_norm": 3193.298828125,
+      "learning_rate": 0.0,
+      "loss": 142.5536,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 600,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}