Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

added_tokens.json +4 -0
gliner_config.json +132 -0
pytorch_model.bin +3 -0
special_tokens_map.json +37 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +64 -0
trainer_state.json +113 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "<<ENT>>": 32000,
+  "<<SEP>>": 32001
+}

gliner_config.json ADDED Viewed

	@@ -0,0 +1,132 @@

+{
+  "class_token_index": 32000,
+  "dropout": 0.4,
+  "embed_ent_token": false,
+  "encoder_config": {
+    "_name_or_path": "knowledgator/Sheared-LLaMA-encoder-1.3B",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaBiModel"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "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": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 5504,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "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": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32002
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 3000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 2048,
+  "label_smoothing": 0.0001,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "llama",
+  "loss_alpha": 0.8,
+  "loss_gamma": 2,
+  "loss_reduction": "sum",
+  "lr_encoder": "8e-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": "knowledgator/Sheared-LLaMA-encoder-1.3B",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 3,
+  "num_steps": 9000,
+  "post_fusion_schema": "",
+  "prev_path": null,
+  "random_drop": true,
+  "root_dir": "gliner_logs",
+  "save_total_limit": 3,
+  "scheduler_type": "linear",
+  "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": 32002,
+  "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:c32c1d5ef4f090b497296db17ff0d1449923669c2cc28ad38c2812d02d70d646
+size 5824576326

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "_",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

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

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,64 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29918": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,113 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.046207497820401,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08718395815170009,
+      "grad_norm": 492.52783203125,
+      "learning_rate": 5.833333333333333e-06,
+      "loss": 21.8384,
+      "step": 100
+    },
+    {
+      "epoch": 0.17436791630340018,
+      "grad_norm": 143.71047973632812,
+      "learning_rate": 6.481481481481481e-06,
+      "loss": 19.3308,
+      "step": 200
+    },
+    {
+      "epoch": 0.26155187445510025,
+      "grad_norm": 805.2228393554688,
+      "learning_rate": 5.833333333333333e-06,
+      "loss": 21.3734,
+      "step": 300
+    },
+    {
+      "epoch": 0.34873583260680036,
+      "grad_norm": 405.0468444824219,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 19.1667,
+      "step": 400
+    },
+    {
+      "epoch": 0.43591979075850046,
+      "grad_norm": 632.6600952148438,
+      "learning_rate": 4.537037037037037e-06,
+      "loss": 17.4984,
+      "step": 500
+    },
+    {
+      "epoch": 0.5231037489102005,
+      "grad_norm": 890.8648071289062,
+      "learning_rate": 3.888888888888889e-06,
+      "loss": 16.9422,
+      "step": 600
+    },
+    {
+      "epoch": 0.6102877070619006,
+      "grad_norm": 243.8746337890625,
+      "learning_rate": 3.2407407407407406e-06,
+      "loss": 19.9537,
+      "step": 700
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "grad_norm": 408.9120178222656,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 18.6301,
+      "step": 800
+    },
+    {
+      "epoch": 0.7846556233653008,
+      "grad_norm": 171.10406494140625,
+      "learning_rate": 1.9444444444444444e-06,
+      "loss": 15.2552,
+      "step": 900
+    },
+    {
+      "epoch": 0.8718395815170009,
+      "grad_norm": 236.40130615234375,
+      "learning_rate": 1.2962962962962962e-06,
+      "loss": 14.5902,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9590235396687009,
+      "grad_norm": 386.51702880859375,
+      "learning_rate": 6.481481481481481e-07,
+      "loss": 12.5311,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 508.4683532714844,
+      "eval_runtime": 15.2151,
+      "eval_samples_per_second": 67.038,
+      "eval_steps_per_second": 8.413,
+      "step": 1147
+    },
+    {
+      "epoch": 1.046207497820401,
+      "grad_norm": 72.9695053100586,
+      "learning_rate": 0.0,
+      "loss": 13.603,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}