Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  "<<ENT>>": 151646,
+  "<<SEP>>": 151647,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "[UNK]": 151648
+}

gliner_config.json

@@ -0,0 +1,132 @@
+{
+  "class_token_index": 151646,
+  "dropout": 0.4,
+  "embed_ent_token": false,
+  "encoder_config": {
+    "_name_or_path": "knowledgator/Qwen2-1.5B-Instruct-checkpint30000",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "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": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "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-06,
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": 32768,
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151648
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 3000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 2048,
+  "label_smoothing": 0.0,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "models/qwen",
+  "loss_alpha": 0.75,
+  "loss_gamma": -1,
+  "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": 30,
+  "max_width": 12,
+  "model_name": "knowledgator/Qwen2-1.5B-Instruct-checkpint30000",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 1,
+  "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": 151648,
+  "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 sha256:23fceb25e4d7b2391ad53746befeb67e6fc2e1b76178b208ca070a6ef7a983e1
+size 6890734142

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd00744ebc35e5532da684a65603111bad31e08a85efc9d4befec6090d572a3
+size 14244

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "_",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,76 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "62": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "mask_token": "_",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -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": 1260.8033447265625,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 14.8341,
+      "step": 100
+    },
+    {
+      "epoch": 0.17436791630340018,
+      "grad_norm": 745.888427734375,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 15.6171,
+      "step": 200
+    },
+    {
+      "epoch": 0.26155187445510025,
+      "grad_norm": 840.9533081054688,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 15.8498,
+      "step": 300
+    },
+    {
+      "epoch": 0.34873583260680036,
+      "grad_norm": 373.6918029785156,
+      "learning_rate": 7.407407407407406e-07,
+      "loss": 16.6859,
+      "step": 400
+    },
+    {
+      "epoch": 0.43591979075850046,
+      "grad_norm": 580.3277587890625,
+      "learning_rate": 6.481481481481481e-07,
+      "loss": 14.4898,
+      "step": 500
+    },
+    {
+      "epoch": 0.5231037489102005,
+      "grad_norm": 77.99569702148438,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 15.7702,
+      "step": 600
+    },
+    {
+      "epoch": 0.6102877070619006,
+      "grad_norm": 147.39584350585938,
+      "learning_rate": 4.6296296296296297e-07,
+      "loss": 15.0814,
+      "step": 700
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "grad_norm": 141.38795471191406,
+      "learning_rate": 3.703703703703703e-07,
+      "loss": 12.6944,
+      "step": 800
+    },
+    {
+      "epoch": 0.7846556233653008,
+      "grad_norm": 947.9025268554688,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 12.4095,
+      "step": 900
+    },
+    {
+      "epoch": 0.8718395815170009,
+      "grad_norm": 862.9531860351562,
+      "learning_rate": 1.8518518518518516e-07,
+      "loss": 12.4597,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9590235396687009,
+      "grad_norm": 247.12240600585938,
+      "learning_rate": 9.259259259259258e-08,
+      "loss": 11.3951,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 476.5635681152344,
+      "eval_runtime": 22.3653,
+      "eval_samples_per_second": 45.606,
+      "eval_steps_per_second": 5.723,
+      "step": 1147
+    },
+    {
+      "epoch": 1.046207497820401,
+      "grad_norm": 573.4383544921875,
+      "learning_rate": 0.0,
+      "loss": 12.2434,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 600,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}