First model version

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "DeepPavlov/bert-base-cased-conversational",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_results.txt

@@ -0,0 +1,11 @@
+auprc = 0.8521416825124468
+auroc = 0.9829215932051185
+eval_loss = 0.10429062761880226
+f1 = 0.7439024390243902
+fn = 62
+fp = 22
+mcc = 0.7325188063848223
+precision = 0.8472222222222222
+recall = 0.6630434782608695
+tn = 2302
+tp = 122

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": "/scratch/mt4493/twitter_labor/trained_models/US/DeepPavlov-bert-base-cased-conversational_jul22_iter8_8850801_seed-7/is_hired_1mo/models/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": "auroc", "early_stopping_metric_minimize": false, "early_stopping_patience": 11, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 73, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": 7, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "DeepPavlov/bert-base-cased-conversational", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "/scratch/mt4493/twitter_labor/trained_models/US/DeepPavlov-bert-base-cased-conversational_jul22_iter8_8850801_seed-7/is_hired_1mo/models", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 46, "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": "runs/8850801_is_hired_1mo/", "thread_count": null, "tokenizer_name": "DeepPavlov/bert-base-cased-conversational", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 440, "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": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55062e4ed0edc339f9a466d58264e7b5b7eaebcb0c23b50a7e4af858c6a8066
+size 866620625

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3efff43f9ab8e0925f41bd70d7e5ef744e1c5042ce6ca8d0e0b1d71e3c20a1
+size 433336585

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8281baf5e7ac4e9bd5b463e7e2968429364eb7ad270c157e9bc6a83e5b2c1999
+size 559

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": "/home/mt4493/.cache/huggingface/transformers/e400007653a8f46a88b57ff3ae2170756b36752a45b633f6554cce43104a6987.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/bert-base-cased-conversational", "do_basic_tokenize": true, "never_split": null}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef9696a51bc1cf79773819ff73fc41e851a6368c95de489b22d2b42e6131f41
+size 3439