Add best model files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,12 @@
+accuracy = 0.9896124650419497
+auprc = 0.9810859562473818
+auroc = 0.9944400284483118
+eval_loss = 0.04591471583092624
+f1 = 0.9602446483180428
+fn = 16
+fp = 10
+mcc = 0.9543241015678982
+precision = 0.9515151515151515
+recall = 0.9691358024691358
+tn = 2163
+tp = 314

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_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/roberta/probing_FINAL_MODEL/best_model_all_transcripts", "cache_dir": "outputs/roberta/probing_FINAL_MODEL/cache", "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": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 312, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 2, "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": 256, "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/roberta/probing_FINAL_MODEL", "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": false, "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": "outputs/roberta/probing_FINAL_MODEL/tensorboard", "thread_count": null, "tokenizer_name": "roberta-base", "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": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"reinit": true}, "wandb_project": "probing_all_transcripts", "warmup_ratio": 0.06, "warmup_steps": 47, "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}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8dc202be11cb329273c739a690802695bed8215e13c26ed8869e3d38b0ed96
+size 498662069

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4016b4f98001206759a4745f25035c2102a676befd6a85b3a15cf4f23f57f2
+size 3451

training_progress_scores.csv

@@ -0,0 +1,8 @@
+global_step,train_loss,mcc,tp,tn,fp,fn,auroc,auprc,accuracy,precision,recall,f1,eval_loss
+156,0.033953532576560974,0.0,0,2173,0,330,0.890560459635471,0.5538107100572817,0.8681582101478226,0.0,0.0,0.0,0.3129343315363882
+312,0.4402586817741394,0.496996966674714,111,2153,20,219,0.9513966168821207,0.7522877261196652,0.9045145825009988,0.33636363636363636,0.8473282442748091,0.48156182212581344,0.21897576025913293
+312,0.4656253159046173,0.496996966674714,111,2153,20,219,0.9513966168821207,0.7522877261196652,0.9045145825009988,0.33636363636363636,0.8473282442748091,0.48156182212581344,0.21897576025913293
+468,0.034133270382881165,0.7900586935428963,263,2122,51,67,0.9758286965373941,0.8855286926860256,0.9528565721134639,0.796969696969697,0.8375796178343949,0.8167701863354038,0.12660043468005575
+624,0.388778418302536,0.915449026165319,302,2153,20,28,0.9916230877574641,0.9660766807943442,0.9808230123851378,0.9151515151515152,0.937888198757764,0.9263803680981596,0.06539175433207886
+624,0.018435971811413765,0.915449026165319,302,2153,20,28,0.9916230877574641,0.9660766807943442,0.9808230123851378,0.9151515151515152,0.937888198757764,0.9263803680981596,0.06539175433207886
+780,0.011490317061543465,0.9543241015678982,314,2163,10,16,0.9944400284483118,0.9810859562473818,0.9896124650419497,0.9515151515151515,0.9691358024691358,0.9602446483180428,0.04591471583092624