manuto59 commited on
Commit
0723100
1 Parent(s): f574742

add model files

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DeepPavlov/bert-base-cased-conversational",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "output_past": true,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.6.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 28996
25
+ }
eval_results.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ auprc = 0.6867624034076988
2
+ auroc = 0.9495127928562518
3
+ eval_loss = 0.13289384448307248
4
+ f1 = 0.6589147286821706
5
+ fn = 29
6
+ fp = 59
7
+ mcc = 0.6455219171675735
8
+ precision = 0.5902777777777778
9
+ recall = 0.7456140350877193
10
+ tn = 2332
11
+ tp = 85
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_epsilon": 1e-08, "best_model_dir": "/scratch/mt4493/twitter_labor/trained_models/US/DeepPavlov-bert-base-cased-conversational_jul22_iter8_8850799_seed-5/lost_job_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": 5, "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_8850799_seed-5/lost_job_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/8850799_lost_job_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": 439, "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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402dabd8dd8d93056f6a6a99f7a8d1faa4006a1d538771d622fd6c860e8d8530
3
+ size 866620625
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a4941768fae096643f2f776b36336c758a0e24f3ea74a093f62a8cd371e16
3
+ size 433336585
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447dd4cea2ba055f247f1f7c23bf319c99fd31353fd6ce81f4939bb978b9dbc6
3
+ size 559
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d523bdc499d1ab7d8f1124dbc3b0eb41a5d8a8ed31b3612c3ec815eaabd28b3
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff