Sami classifier NbAiLab-nb-bert-base_sami_sami_20210531-121715_chunks-200words_pred_e3.0_lr3e-06_wr0.1_wd0.0_s608_st0.75_r1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "NbAiLab/nb-bert-base",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.txt

@@ -0,0 +1,10 @@
+accuracy = 0.9585613760750586
+eval_loss = 0.23575447580824774
+f1 = 0.9506976744186045
+fn = 10
+fp = 43
+mcc = 0.9163010143688998
+precision = 0.9223826714801444
+recall = 0.980806142034549
+tn = 715
+tp = 511

model_args.json

@@ -0,0 +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": "utf-8", "eval_batch_size": 28, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 10000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-06, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "NbAiLab/nb-bert-base", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3.0, "optimizer": "AdamW", "output_dir": "output/NbAiLab-nb-bert-base_sami_sami_20210531-121715_chunks-200words_pred_e3.0_lr3e-06_wr0.1_wd0.0_s608_st0.75_r1", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 94, "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": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "NbAiLab/nb-bert-base", "tokenizer_type": null, "train_batch_size": 28, "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": {"entity": "nbailab", "project": "sami-chunk", "name": "NbAiLab-nb-bert-base_sami_sami_20210531-121715_chunks-200words_pred_e3.0_lr3e-06_wr0.1_wd0.0_s608_st0.75_r1", "sync_tensorboard": true}, "wandb_project": null, "warmup_ratio": 0.1, "warmup_steps": 9699, "weight_decay": 0.0, "model_class": "ClassificationModel", "labels_list": [0, 1], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": true, "special_tokens_list": [], "stride": 0.75, "tie_value": 1}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ecc5729f63877fd1f9a40ef8bfa72db4e3b11aada23504119527e1242e6e50f
+size 711504045

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "NbAiLab/nb-bert-base", "do_basic_tokenize": true, "never_split": null}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c91c4225b7cde5415204dfa61aaa00c321582cccd83920acc6a5c22c146756
+size 3439

training_progress_scores.csv

@@ -0,0 +1,13 @@
+global_step,tp,tn,fp,fn,mcc,train_loss,eval_loss,f1,precision,recall,accuracy
+10000,508,706,52,13,0.8977122158321943,0.016092317178845406,0.12647712647240653,0.9398704902867716,0.9071428571428571,0.9750479846449136,0.9491790461297889
+20000,504,722,36,17,0.9150907035740606,0.000561795081011951,0.15973145561959357,0.9500471253534402,0.9333333333333333,0.9673704414587332,0.9585613760750586
+30000,512,711,47,9,0.9120297554719166,0.0016663457499817014,0.1817829882242559,0.9481481481481482,0.9159212880143113,0.982725527831094,0.9562157935887412
+32328,513,692,66,8,0.8860031552889174,0.002664804458618164,0.19140609940741873,0.9327272727272728,0.8860103626943006,0.9846449136276392,0.9421422986708365
+40000,507,722,36,14,0.9201412525832662,0.0029837745241820812,0.17858079713677033,0.9530075187969925,0.9337016574585635,0.9731285988483686,0.9609069585613761
+50000,509,716,42,12,0.9143970940378516,0.0077561563812196255,0.1778221957151819,0.9496268656716419,0.9237749546279492,0.9769673704414588,0.9577795152462861
+60000,508,716,42,13,0.9126951496089721,0.0012778086820617318,0.2027259276812043,0.9486461251167133,0.9236363636363636,0.9750479846449136,0.9569976544175137
+64656,512,721,37,9,0.9270693418857209,0.00011811653530457988,0.19937212274705546,0.9570093457943926,0.9326047358834244,0.982725527831094,0.9640344018764659
+70000,510,709,49,11,0.9056135993413006,0.00012433102529030293,0.22229803307375579,0.9444444444444443,0.9123434704830053,0.9788867562380038,0.9530883502736512
+80000,511,718,40,10,0.920824053884389,0.2281501591205597,0.22179906898585944,0.9533582089552238,0.9274047186932849,0.980806142034549,0.9609069585613761
+90000,512,717,41,9,0.921017790418457,0.0004354757838882506,0.23509133785619224,0.9534450651769086,0.9258589511754068,0.982725527831094,0.9609069585613761
+96984,511,715,43,10,0.9163010143688998,0.0017305811634287238,0.23575447580824774,0.9506976744186045,0.9223826714801444,0.980806142034549,0.9585613760750586