Upload folder using huggingface_hub

Browse files

Files changed (9) hide show

added_tokens.json +3 -0
gliner_config.json +214 -0
pytorch_model.bin +3 -0
rng_state.pth +3 -0
special_tokens_map.json +51 -0
spm.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +58 -0
trainer_state.json +163 -0

added_tokens.json ADDED Viewed

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

+{
+  "[MASK]": 128000
+}

gliner_config.json ADDED Viewed

	@@ -0,0 +1,214 @@

+{
+  "class_token_index": -1,
+  "dropout": 0.3,
+  "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": 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": 0.0,
+    "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": 1.0,
+    "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": 1.0,
+    "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": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "log_dir": "deberta/",
+  "loss_alpha": 0.75,
+  "loss_gamma": 2,
+  "loss_reduction": "sum",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_grad_norm": 10.0,
+  "max_len": 512,
+  "max_neg_type_ratio": 1,
+  "max_types": 100,
+  "max_width": 12,
+  "model_name": "microsoft/deberta-v3-small",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_steps": 100000,
+  "post_fusion_schema": "l2l-l2t-t2l",
+  "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": "4.40.2",
+  "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"
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:96573b5234eb8e56696e9f452af230f38a3b67fe3f351b89c385dacaba2e1358
+size 832259818

rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8233421556158558e19337497b3965c5a35363adaf30da78ed1bdec1b3b58a41
+size 14244

special_tokens_map.json ADDED Viewed

	@@ -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 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 +1,58 @@

+{
+  "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": 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 ADDED Viewed

	@@ -0,0 +1,163 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2941626306398164,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1274534794799898,
+      "grad_norm": 855.9707641601562,
+      "learning_rate": 9.999156208166614e-06,
+      "loss": 74.3469,
+      "step": 500
+    },
+    {
+      "epoch": 0.2549069589599796,
+      "grad_norm": 302.50543212890625,
+      "learning_rate": 9.89824533543787e-06,
+      "loss": 61.1889,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3823604384399694,
+      "grad_norm": 495.7685546875,
+      "learning_rate": 9.632470336074009e-06,
+      "loss": 57.9995,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5098139179199592,
+      "grad_norm": 265.8482666015625,
+      "learning_rate": 9.21077660993783e-06,
+      "loss": 57.4618,
+      "step": 2000
+    },
+    {
+      "epoch": 0.637267397399949,
+      "grad_norm": 1070.9898681640625,
+      "learning_rate": 8.647357437093104e-06,
+      "loss": 53.0734,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7647208768799388,
+      "grad_norm": 607.1848754882812,
+      "learning_rate": 7.961176263324902e-06,
+      "loss": 54.122,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8921743563599286,
+      "grad_norm": 299.444091796875,
+      "learning_rate": 7.175328432410367e-06,
+      "loss": 55.9574,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2435.821044921875,
+      "eval_runtime": 13.0829,
+      "eval_samples_per_second": 266.532,
+      "eval_steps_per_second": 33.326,
+      "step": 3923
+    },
+    {
+      "epoch": 1.0196278358399185,
+      "grad_norm": 313.2464294433594,
+      "learning_rate": 6.3162638478229965e-06,
+      "loss": 52.9767,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1470813153199082,
+      "grad_norm": 406.19097900390625,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 49.7189,
+      "step": 4500
+    },
+    {
+      "epoch": 1.274534794799898,
+      "grad_norm": 227.44325256347656,
+      "learning_rate": 4.495632414398659e-06,
+      "loss": 48.3298,
+      "step": 5000
+    },
+    {
+      "epoch": 1.401988274279888,
+      "grad_norm": 292.7037353515625,
+      "learning_rate": 3.595344001132154e-06,
+      "loss": 50.4245,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5294417537598777,
+      "grad_norm": 522.2669677734375,
+      "learning_rate": 2.7423332084455543e-06,
+      "loss": 49.8634,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6568952332398674,
+      "grad_norm": 408.0614929199219,
+      "learning_rate": 1.965310496864217e-06,
+      "loss": 49.0125,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7843487127198574,
+      "grad_norm": 722.4154052734375,
+      "learning_rate": 1.290428735823593e-06,
+      "loss": 44.8823,
+      "step": 7000
+    },
+    {
+      "epoch": 1.911802192199847,
+      "grad_norm": 383.4438171386719,
+      "learning_rate": 7.404029558083653e-07,
+      "loss": 47.8235,
+      "step": 7500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2325.86083984375,
+      "eval_runtime": 13.1669,
+      "eval_samples_per_second": 264.831,
+      "eval_steps_per_second": 33.113,
+      "step": 7846
+    },
+    {
+      "epoch": 2.039255671679837,
+      "grad_norm": 408.5860290527344,
+      "learning_rate": 3.337458105627145e-07,
+      "loss": 44.1611,
+      "step": 8000
+    },
+    {
+      "epoch": 2.166709151159827,
+      "grad_norm": 252.09278869628906,
+      "learning_rate": 8.414448202622494e-08,
+      "loss": 45.9323,
+      "step": 8500
+    },
+    {
+      "epoch": 2.2941626306398164,
+      "grad_norm": 174.15538024902344,
+      "learning_rate": 0.0,
+      "loss": 47.7162,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}