Add best model

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 = 0.9876148621654015
+auprc = 0.9927429305166631
+auroc = 0.9954820021299254
+eval_loss = 0.08333356069090714
+f1 = 0.9749393694421989
+fn = 22
+fp = 9
+mcc = 0.9668097666513458
+precision = 0.9648
+recall = 0.9852941176470589
+tn = 1869
+tp = 603

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/adding_on_FINAL_MODEL/best_model_all_transcripts", "cache_dir": "outputs/roberta/adding_on_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": 469, "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/adding_on_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/adding_on_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": "adding_on_all_transcripts", "warmup_ratio": 0.06, "warmup_steps": 71, "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 sha256:122eaaa022ab475b13b08aadb676588bb348eda12d30451d21596ef60041de9f
+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:b95da818902114578a4d0d1dac4183a0d9039f6150c797cc95d1eac55435fa01
+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
+235,0.8629159927368164,0.641157540126694,563,1526,352,62,0.9296536741214059,0.8059950625747473,0.8345984818218138,0.9008,0.6153005464480874,0.7311688311688312,0.33063958536464566
+469,0.11309435963630676,0.8541629151798243,558,1808,70,67,0.9817005324813631,0.9481751215623047,0.9452656811825809,0.8928,0.8885350318471338,0.8906624102154829,0.1476815326590115
+470,0.37224850058555603,0.8428687233177999,533,1825,53,92,0.9814185303514378,0.9476805396095412,0.9420695165801038,0.8528,0.909556313993174,0.8802642444260941,0.15699649642120464
+705,0.004011260811239481,0.8507765192484604,496,1869,9,129,0.987396805111821,0.9734036435804934,0.9448661606072712,0.7936,0.9821782178217822,0.8778761061946901,0.25879878599993356
+938,0.0033488196786493063,0.9581912741072777,596,1868,10,29,0.9937661341853036,0.9879528947532448,0.9844186975629244,0.9536,0.9834983498349835,0.9683184402924453,0.09167598592708431
+940,0.10869354754686356,0.9657404249473905,603,1868,10,22,0.9942057507987221,0.9886196435688359,0.9872153415900919,0.9648,0.9836867862969005,0.9741518578352181,0.08491238276939095
+1175,0.0013148263096809387,0.9668097666513458,603,1869,9,22,0.9954820021299254,0.9927429305166631,0.9876148621654015,0.9648,0.9852941176470589,0.9749393694421989,0.08333356069090714