update models

config.json

@@ -94,49 +94,7 @@
     "80": "LABEL_80",
     "81": "LABEL_81",
     "82": "LABEL_82",
-    "83": "LABEL_83",
-    "84": "LABEL_84",
-    "85": "LABEL_85",
-    "86": "LABEL_86",
-    "87": "LABEL_87",
-    "88": "LABEL_88",
-    "89": "LABEL_89",
-    "90": "LABEL_90",
-    "91": "LABEL_91",
-    "92": "LABEL_92",
-    "93": "LABEL_93",
-    "94": "LABEL_94",
-    "95": "LABEL_95",
-    "96": "LABEL_96",
-    "97": "LABEL_97",
-    "98": "LABEL_98",
-    "99": "LABEL_99",
-    "100": "LABEL_100",
-    "101": "LABEL_101",
-    "102": "LABEL_102",
-    "103": "LABEL_103",
-    "104": "LABEL_104",
-    "105": "LABEL_105",
-    "106": "LABEL_106",
-    "107": "LABEL_107",
-    "108": "LABEL_108",
-    "109": "LABEL_109",
-    "110": "LABEL_110",
-    "111": "LABEL_111",
-    "112": "LABEL_112",
-    "113": "LABEL_113",
-    "114": "LABEL_114",
-    "115": "LABEL_115",
-    "116": "LABEL_116",
-    "117": "LABEL_117",
-    "118": "LABEL_118",
-    "119": "LABEL_119",
-    "120": "LABEL_120",
-    "121": "LABEL_121",
-    "122": "LABEL_122",
-    "123": "LABEL_123",
-    "124": "LABEL_124",
-    "125": "LABEL_125"
+    "83": "LABEL_83"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -144,34 +102,8 @@
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_10": 10,
-    "LABEL_100": 100,
-    "LABEL_101": 101,
-    "LABEL_102": 102,
-    "LABEL_103": 103,
-    "LABEL_104": 104,
-    "LABEL_105": 105,
-    "LABEL_106": 106,
-    "LABEL_107": 107,
-    "LABEL_108": 108,
-    "LABEL_109": 109,
     "LABEL_11": 11,
-    "LABEL_110": 110,
-    "LABEL_111": 111,
-    "LABEL_112": 112,
-    "LABEL_113": 113,
-    "LABEL_114": 114,
-    "LABEL_115": 115,
-    "LABEL_116": 116,
-    "LABEL_117": 117,
-    "LABEL_118": 118,
-    "LABEL_119": 119,
     "LABEL_12": 12,
-    "LABEL_120": 120,
-    "LABEL_121": 121,
-    "LABEL_122": 122,
-    "LABEL_123": 123,
-    "LABEL_124": 124,
-    "LABEL_125": 125,
     "LABEL_13": 13,
     "LABEL_14": 14,
     "LABEL_15": 15,
@@ -250,23 +182,7 @@
     "LABEL_81": 81,
     "LABEL_82": 82,
     "LABEL_83": 83,
-    "LABEL_84": 84,
-    "LABEL_85": 85,
-    "LABEL_86": 86,
-    "LABEL_87": 87,
-    "LABEL_88": 88,
-    "LABEL_89": 89,
-    "LABEL_9": 9,
-    "LABEL_90": 90,
-    "LABEL_91": 91,
-    "LABEL_92": 92,
-    "LABEL_93": 93,
-    "LABEL_94": 94,
-    "LABEL_95": 95,
-    "LABEL_96": 96,
-    "LABEL_97": 97,
-    "LABEL_98": 98,
-    "LABEL_99": 99
+    "LABEL_9": 9
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

model_args.json

@@ -1 +1 @@
-{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "roberta-base", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 4, "weight_decay": 0.0, "model_class": "MultiLabelClassificationModel", "sliding_window": false, "stride": 0.8, "threshold": 0.5, "tie_value": 1, "labels_list": [], "labels_map": {}, "lazy_loading": false, "special_tokens_list": []}
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "roberta-base", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 6, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 3, "weight_decay": 0.0, "model_class": "MultiLabelClassificationModel", "sliding_window": false, "stride": 0.8, "threshold": 0.5, "tie_value": 1, "labels_list": [], "labels_map": {}, "lazy_loading": false, "special_tokens_list": []}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960f1151ad13b50357396d7ae2a5726bb8befbac3c0c5b0e076a24e70530f360
-size 501418601
+oid sha256:a7359a64f7ac60b11e4347b3abdd42df81ae484eafb169932fb8d8078dcceebe
+size 501289449

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3b3a2da7d9bd8647168d70d64cc07829d39d3f896e827082dfd311213eeebf
+oid sha256:3ce85e0f40402828049238da313ad4b732e6efa682dca78dfe6fed583681441e
 size 2991