Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

added_tokens.json +3 -0
gliner_config.json +217 -0
pytorch_model.bin +3 -0
special_tokens_map.json +51 -0
spm.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +58 -0
trainer_state.json +179 -0

added_tokens.json ADDED Viewed

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

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

gliner_config.json ADDED Viewed

	@@ -0,0 +1,217 @@

+{
+  "class_token_index": -1,
+  "dropout": 0.4,
+  "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": "sentence-transformers/all-MiniLM-L6-v2",
+  "labels_encoder_config": {
+    "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+    "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,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "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": 6,
+    "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": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "log_dir": "biencoder/",
+  "loss_alpha": -1,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_grad_norm": 10.0,
+  "max_len": 386,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 12,
+  "model_name": "microsoft/deberta-v3-small",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_steps": 120000,
+  "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": "4.40.2",
+  "val_data_dir": "none",
+  "vocab_size": -1,
+  "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 sha256:13bb508286910c23fd3c0260759389521add1863bf71c4f468c9dec3c7d1aea5
+size 756513098

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 +1,179 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0558810274898605,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22532672374943669,
+      "grad_norm": 1464.645751953125,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 419.737,
+      "step": 500
+    },
+    {
+      "epoch": 0.45065344749887337,
+      "grad_norm": 3850.259033203125,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 377.5664,
+      "step": 1000
+    },
+    {
+      "epoch": 0.67598017124831,
+      "grad_norm": 1552.3658447265625,
+      "learning_rate": 5e-06,
+      "loss": 359.1407,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9013068949977467,
+      "grad_norm": 1931.043212890625,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 363.6383,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 337.4689025878906,
+      "eval_runtime": 13.0417,
+      "eval_samples_per_second": 151.284,
+      "eval_steps_per_second": 18.939,
+      "step": 2219
+    },
+    {
+      "epoch": 1.1266336187471835,
+      "grad_norm": 1212.9539794921875,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 344.8475,
+      "step": 2500
+    },
+    {
+      "epoch": 1.35196034249662,
+      "grad_norm": 1241.7996826171875,
+      "learning_rate": 1e-05,
+      "loss": 350.3084,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5772870662460567,
+      "grad_norm": 2845.786376953125,
+      "learning_rate": 9.991540791356342e-06,
+      "loss": 341.8033,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8026137899954935,
+      "grad_norm": 1714.59423828125,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 337.2936,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 326.2698974609375,
+      "eval_runtime": 13.0537,
+      "eval_samples_per_second": 151.145,
+      "eval_steps_per_second": 18.922,
+      "step": 4438
+    },
+    {
+      "epoch": 2.0279405137449302,
+      "grad_norm": 2061.15966796875,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 338.1808,
+      "step": 4500
+    },
+    {
+      "epoch": 2.253267237494367,
+      "grad_norm": 1502.1851806640625,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 325.4306,
+      "step": 5000
+    },
+    {
+      "epoch": 2.4785939612438037,
+      "grad_norm": 1462.711669921875,
+      "learning_rate": 9.789947561577445e-06,
+      "loss": 320.5629,
+      "step": 5500
+    },
+    {
+      "epoch": 2.70392068499324,
+      "grad_norm": 3903.998046875,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 322.1042,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9292474087426768,
+      "grad_norm": 1786.909423828125,
+      "learning_rate": 9.591080534401371e-06,
+      "loss": 327.4969,
+      "step": 6500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 320.3514099121094,
+      "eval_runtime": 13.0727,
+      "eval_samples_per_second": 150.926,
+      "eval_steps_per_second": 18.894,
+      "step": 6657
+    },
+    {
+      "epoch": 3.1545741324921135,
+      "grad_norm": 1130.3773193359375,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 300.7485,
+      "step": 7000
+    },
+    {
+      "epoch": 3.3799008562415502,
+      "grad_norm": 1423.0567626953125,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 312.8204,
+      "step": 7500
+    },
+    {
+      "epoch": 3.605227579990987,
+      "grad_norm": 1232.428955078125,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 307.7865,
+      "step": 8000
+    },
+    {
+      "epoch": 3.8305543037404237,
+      "grad_norm": 1071.1146240234375,
+      "learning_rate": 9.01061596377522e-06,
+      "loss": 295.8372,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 318.1500244140625,
+      "eval_runtime": 13.0462,
+      "eval_samples_per_second": 151.232,
+      "eval_steps_per_second": 18.933,
+      "step": 8876
+    },
+    {
+      "epoch": 4.0558810274898605,
+      "grad_norm": 2371.276123046875,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 303.3605,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 30000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 14,
+  "save_steps": 3000,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}