Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<<EXAMPLE>>": 128003,
+  "<<LABEL>>": 128001,
+  "<<SEP>>": 128002,
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,151 @@
+{
+  "architecture_type": "uni-encoder",
+  "architectures": [
+    "GLiClassModel"
+  ],
+  "bos_token_id": 1,
+  "class_token_index": 128001,
+  "class_token_pooling": "average",
+  "contrastive_loss_coef": 0.0,
+  "dropout": 0.3,
+  "dtype": "float32",
+  "embed_class_token": true,
+  "encoder_config": {
+    "_name_or_path": "microsoft/deberta-v3-base",
+    "attention_probs_dropout_prob": 0.1,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-07,
+    "legacy": true,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "model_type": "deberta-v2",
+    "norm_rel_ebd": "layer_norm",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pooler_dropout": 0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 768,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": false,
+    "position_buckets": 256,
+    "relative_attention": true,
+    "share_att_key": true,
+    "type_vocab_size": 0,
+    "vocab_size": 128004
+  },
+  "encoder_layer_id": -1,
+  "encoder_model_name": "microsoft/deberta-v3-base",
+  "eos_token_id": 2,
+  "example_token_index": 128003,
+  "extract_text_features": false,
+  "focal_loss_alpha": 0.8,
+  "focal_loss_gamma": -1,
+  "focal_loss_reduction": "none",
+  "hidden_size": 768,
+  "ignore_index": -100,
+  "initializer_range": 0.03,
+  "label_model_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,
+    "dtype": "float32",
+    "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,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "label_model_name": "BAAI/bge-small-en-v1.5",
+  "layer_wise": false,
+  "logit_scale_init_value": 2.6592,
+  "max_num_classes": 25,
+  "model_type": "GLiClass",
+  "normalize_features": false,
+  "pad_token_id": 0,
+  "pooling_strategy": "first",
+  "problem_type": "multi_label_classification",
+  "projector_hidden_act": "gelu",
+  "prompt_first": true,
+  "scorer_type": "mlp",
+  "shuffle_labels": true,
+  "squeeze_layers": false,
+  "text_token_index": 128002,
+  "transformers_version": "4.57.3",
+  "use_lstm": false,
+  "use_segment_embeddings": true,
+  "vocab_size": 128004
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6ce13c9ca472a72bded2f0333534d5631aa52b6eb5b38d5df32b080501e4b6
+size 746224192

special_tokens_map.json

@@ -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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "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
+    },
+    "128001": {
+      "content": "<<LABEL>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<<EXAMPLE>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "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

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.96,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 3.8120243549346924,
+      "learning_rate": 9.938823863528065e-06,
+      "loss": 0.0004,
+      "step": 100
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.0018049710197374225,
+      "learning_rate": 9.428445774703444e-06,
+      "loss": 0.0004,
+      "step": 200
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.001558819436468184,
+      "learning_rate": 8.450931618533601e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.1837037037037037,
+      "grad_norm": 0.0011788058327510953,
+      "learning_rate": 7.109394799115268e-06,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.0010272902436554432,
+      "learning_rate": 5.545347771586018e-06,
+      "loss": 0.004,
+      "step": 500
+    },
+    {
+      "epoch": 1.7762962962962963,
+      "grad_norm": 0.0011670357780531049,
+      "learning_rate": 3.92377455398589e-06,
+      "loss": 0.0001,
+      "step": 600
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 0.0010163792176172137,
+      "learning_rate": 2.4157273335425296e-06,
+      "loss": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 2.3674074074074074,
+      "grad_norm": 0.0008961952407844365,
+      "learning_rate": 1.1802829701224183e-06,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 2.6637037037037037,
+      "grad_norm": 0.0008640048909001052,
+      "learning_rate": 3.4776272104986966e-07,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.0008631945238448679,
+      "learning_rate": 5.985260171704199e-09,
+      "loss": 0.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1014,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 102343869414864.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77994fb943ddc9c0f5d60f170ddff38fbc0d75311d69c4211c39ca9796579fac
+size 5969