rigonsallauka
commited on
Commit
•
9501d7d
1
Parent(s):
8cb059b
Upload 10 files
Browse files- config.json +56 -0
- eval_results.txt +5 -0
- model_args.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-PROBLEM",
|
15 |
+
"2": "I-PROBLEM",
|
16 |
+
"3": "E-PROBLEM",
|
17 |
+
"4": "S-PROBLEM",
|
18 |
+
"5": "B-TREATMENT",
|
19 |
+
"6": "I-TREATMENT",
|
20 |
+
"7": "E-TREATMENT",
|
21 |
+
"8": "S-TREATMENT",
|
22 |
+
"9": "B-TEST",
|
23 |
+
"10": "I-TEST",
|
24 |
+
"11": "E-TEST",
|
25 |
+
"12": "S-TEST"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"O": 0,
|
31 |
+
"B-PROBLEM": 1,
|
32 |
+
"I-PROBLEM": 2,
|
33 |
+
"E-PROBLEM": 3,
|
34 |
+
"S-PROBLEM": 4,
|
35 |
+
"B-TREATMENT": 5,
|
36 |
+
"I-TREATMENT": 6,
|
37 |
+
"E-TREATMENT": 7,
|
38 |
+
"S-TREATMENT": 8,
|
39 |
+
"B-TEST": 9,
|
40 |
+
"I-TEST": 10,
|
41 |
+
"E-TEST": 11,
|
42 |
+
"S-TEST": 12
|
43 |
+
},
|
44 |
+
"layer_norm_eps": 1e-12,
|
45 |
+
"max_position_embeddings": 512,
|
46 |
+
"model_type": "bert",
|
47 |
+
"num_attention_heads": 12,
|
48 |
+
"num_hidden_layers": 12,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"position_embedding_type": "absolute",
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.28.0",
|
53 |
+
"type_vocab_size": 2,
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 28996
|
56 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
accuracy = 0.8782103929132794
|
2 |
+
eval_loss = 0.3968946770636102
|
3 |
+
f1_score = 0.7556232119891866
|
4 |
+
precision = 0.7552069671056083
|
5 |
+
recall = 0.7560399159663865
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adam_epsilon": 1e-08, "best_model_dir": "outputs/pl_model_ds/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": true, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 30, "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": 64, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "bert-base-cased", "model_type": "bert", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 200, "optimizer": "AdamW", "output_dir": "outputs/pl_model_ds", "overwrite_output_dir": true, "process_count": 254, "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": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_type": null, "tokenizer_name": null, "train_batch_size": 64, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": "sl-tagging", "warmup_ratio": 0.06, "warmup_steps": 65880, "weight_decay": 0.01, "model_class": "NERModel", "classification_report": true, "labels_list": ["O", "B-PROBLEM", "I-PROBLEM", "E-PROBLEM", "S-PROBLEM", "B-TREATMENT", "I-TREATMENT", "E-TREATMENT", "S-TREATMENT", "B-TEST", "I-TEST", "E-TEST", "S-TEST"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61b47930e9f435a4366c82d30c4262c7be9090fc43900f584f9d68f14ca944a1
|
3 |
+
size 861962733
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b78aa63bf297052dca9a9a7e10888c23528044245e1522f5d35d17c112621395
|
3 |
+
size 430994295
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f2bab54c773ccd1a9ec812292ae6fd4758d53bf0cfb211400d5f94b004692d8
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d6ca27201bd818733d67220f6d16ac1a4d6b736ad5a779dd9d0beecb1f63433
|
3 |
+
size 3055
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|