first commit

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "./unsup-consert-emanuals",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.txt

@@ -0,0 +1,8 @@
+auprc = 0.6058849986315159
+auroc = 0.934235661370731
+eval_loss = 0.1764016634490537
+fn = 73
+fp = 57
+mcc = 0.5580284776888864
+tn = 1594
+tp = 96

model_args.json

@@ -0,0 +1 @@
+{"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, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 197, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 79, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "./unsup-consert-emanuals", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 4, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 38, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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": 197, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_type": null, "tokenizer_name": "./unsup-consert-emanuals", "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": true, "use_early_stopping": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 95, "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 sha256:79f65609041c5246002d9c54492441da262cb16b37b6eb98b4ed966d863a1f70
+size 875996369

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fae2c01fb399200bf6d4a94390d4c2412e95b99bbe01affe52bf11abc3b80f1
+size 438024457

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6327af3220ffb2f475766a7985575826c80704194659edb3124cc82f67b1ab
+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, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/nandy/.cache/huggingface/transformers/534479488c54aeaf9c3406f647aa2ec13648c06771ffe269edabebd4c412da1d.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "./unsup-consert-emanuals", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f19cfd00346ea52585e0641462bb3ec7d85ccf6e4babbda6c62671fc69d1ef
+size 3119