Ashlee Kupor commited on
Commit
e102f04
1 Parent(s): 4f69522

Add model files

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.28.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
eval_results.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ accuracy = 0.9988014382740711
2
+ auprc = 0.999671473774273
3
+ auroc = 0.9999595828954814
4
+ eval_loss = 0.0083527624613688
5
+ f1 = 0.9946332737030411
6
+ fn = 0
7
+ fp = 3
8
+ mcc = 0.9939768224800285
9
+ precision = 1.0
10
+ recall = 0.9893238434163701
11
+ tn = 2222
12
+ tp = 278
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_args.json ADDED
@@ -0,0 +1 @@
 
 
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/revoicing_FINAL_MODEL/best_model_all_transcripts", "cache_dir": "outputs/roberta/revoicing_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": 556, "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/revoicing_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/revoicing_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": "revoicing_all_transcripts", "warmup_ratio": 0.06, "warmup_steps": 84, "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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ca8f0d86870b4a3b5c7f018c668d46b5f6ade861b0897717e112268ac8c3e8
3
+ size 498662069
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "do_lower_case": false,
7
+ "eos_token": "</s>",
8
+ "errors": "replace",
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0a4c564b3913af92731c33a092c81a5665229302e991d2080d9393d913bbbb
3
+ size 3451
training_progress_scores.csv ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ global_step,train_loss,mcc,tp,tn,fp,fn,auroc,auprc,accuracy,precision,recall,f1,eval_loss
2
+ 278,0.043835386633872986,0.6958056755453569,229,2103,122,49,0.9392126748039772,0.7322165696462111,0.9316819816220535,0.8237410071942446,0.6524216524216524,0.7281399046104928,0.18036567747664337
3
+ 556,0.47604700922966003,0.8446817691009906,275,2135,90,3,0.994889661304664,0.9578320447798954,0.9628445864962045,0.9892086330935251,0.7534246575342466,0.8553654743390358,0.12537497816422877
4
+ 556,0.017008347436785698,0.8446817691009906,275,2135,90,3,0.994889661304664,0.9578320447798954,0.9628445864962045,0.9892086330935251,0.7534246575342466,0.8553654743390358,0.12537497816422877
5
+ 834,0.0045775845646858215,0.9485634800565332,277,2199,26,1,0.9992045913830733,0.9922658322093301,0.98921294446664,0.9964028776978417,0.9141914191419142,0.9535283993115318,0.037925365192837235
6
+ 1112,0.0014692647382616997,0.9900124582484787,278,2220,5,0,0.9998593484762752,0.9987380057755086,0.9980023971234518,1.0,0.9823321554770318,0.9910873440285205,0.011930922513499264
7
+ 1112,0.0008262554183602333,0.9900124582484787,278,2220,5,0,0.9998593484762752,0.9987380057755086,0.9980023971234518,1.0,0.9823321554770318,0.9910873440285205,0.011930922513499264
8
+ 1390,0.0001813603739719838,0.9939768224800285,278,2222,3,0,0.9999595828954814,0.999671473774273,0.9988014382740711,1.0,0.9893238434163701,0.9946332737030411,0.0083527624613688
vocab.json ADDED
The diff for this file is too large to render. See raw diff