swardiantara
commited on
Commit
•
16c55dd
1
Parent(s):
fdf3eb3
update to latest version trained by latest dataset
Browse files- config.json +27 -23
- eval_results.txt +4 -0
- model_args.json +1 -1
- ner_drone_290322_1655.h5 +0 -3
- pytorch_model.bin +2 -2
- special_tokens_map.json +7 -1
- tokenizer.json +0 -0
- tokenizer_config.json +16 -1
- training_args.bin +2 -2
- vocab.json +0 -0
config.json
CHANGED
@@ -10,32 +10,36 @@
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
-
"0": "
|
14 |
-
"1": "
|
15 |
-
"2": "
|
16 |
-
"3": "
|
17 |
-
"4": "
|
18 |
-
"5": "
|
19 |
-
"6": "
|
20 |
-
"7": "
|
21 |
-
"8": "
|
22 |
-
"9": "
|
23 |
-
"10": "
|
|
|
|
|
24 |
},
|
25 |
"initializer_range": 0.02,
|
26 |
"intermediate_size": 3072,
|
27 |
"label2id": {
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
|
|
|
|
39 |
},
|
40 |
"layer_norm_eps": 1e-12,
|
41 |
"max_position_embeddings": 512,
|
@@ -45,7 +49,7 @@
|
|
45 |
"pad_token_id": 0,
|
46 |
"position_embedding_type": "absolute",
|
47 |
"torch_dtype": "float32",
|
48 |
-
"transformers_version": "4.
|
49 |
"type_vocab_size": 2,
|
50 |
"use_cache": true,
|
51 |
"vocab_size": 28996
|
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
+
"0": "B-ACTION",
|
14 |
+
"1": "I-ACTION",
|
15 |
+
"2": "O",
|
16 |
+
"3": "B-PARAMETER",
|
17 |
+
"4": "I-PARAMETER",
|
18 |
+
"5": "B-STATE",
|
19 |
+
"6": "I-STATE",
|
20 |
+
"7": "B-COMPONENT",
|
21 |
+
"8": "B-ISSUE",
|
22 |
+
"9": "I-ISSUE",
|
23 |
+
"10": "B-FUNCTION",
|
24 |
+
"11": "I-FUNCTION",
|
25 |
+
"12": "I-COMPONENT"
|
26 |
},
|
27 |
"initializer_range": 0.02,
|
28 |
"intermediate_size": 3072,
|
29 |
"label2id": {
|
30 |
+
"B-ACTION": 0,
|
31 |
+
"B-COMPONENT": 7,
|
32 |
+
"B-FUNCTION": 10,
|
33 |
+
"B-ISSUE": 8,
|
34 |
+
"B-PARAMETER": 3,
|
35 |
+
"B-STATE": 5,
|
36 |
+
"I-ACTION": 1,
|
37 |
+
"I-COMPONENT": 12,
|
38 |
+
"I-FUNCTION": 11,
|
39 |
+
"I-ISSUE": 9,
|
40 |
+
"I-PARAMETER": 4,
|
41 |
+
"I-STATE": 6,
|
42 |
+
"O": 2
|
43 |
},
|
44 |
"layer_norm_eps": 1e-12,
|
45 |
"max_position_embeddings": 512,
|
|
|
49 |
"pad_token_id": 0,
|
50 |
"position_embedding_type": "absolute",
|
51 |
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.24.0",
|
53 |
"type_vocab_size": 2,
|
54 |
"use_cache": true,
|
55 |
"vocab_size": 28996
|
eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.15393207139145074
|
2 |
+
f1_score = 0.8906823184152604
|
3 |
+
precision = 0.8913362701908958
|
4 |
+
recall = 0.8900293255131965
|
model_args.json
CHANGED
@@ -1 +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": "outputs/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": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 16, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16":
|
|
|
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/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": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 16, "evaluate_during_training": false, "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": 0.0001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "bert-base-cased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 4, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 10, "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": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 22, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["B-ACTION", "I-ACTION", "O", "B-PARAMETER", "I-PARAMETER", "B-STATE", "I-STATE", "B-COMPONENT", "B-ISSUE", "I-ISSUE", "B-FUNCTION", "I-FUNCTION", "I-COMPONENT"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
|
ner_drone_290322_1655.h5
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8fa01df682340fa67a8ca518292d844f9995e8ca0838af7e85b3d60b4b85654d
|
3 |
-
size 1091328
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa2fbef864fd518ffabec64a6dcd43166184971956bc484d6fc4933640d7d0d4
|
3 |
+
size 430990829
|
special_tokens_map.json
CHANGED
@@ -1 +1,7 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1,16 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "bert-base-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf430a9b1158b1cf056e37ad4ed459a10ef4207aad754f2310de36625c460f9
|
3 |
+
size 3131
|
vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|