Add model
Browse files- config.json +54 -0
- eval_results.txt +7 -0
- model_args.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4,
|
32 |
+
"LABEL_5": 5,
|
33 |
+
"LABEL_6": 6,
|
34 |
+
"LABEL_7": 7,
|
35 |
+
"LABEL_8": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"max_position_embeddings": 512,
|
39 |
+
"model_type": "bert",
|
40 |
+
"num_attention_heads": 16,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"pooler_fc_size": 768,
|
44 |
+
"pooler_num_attention_heads": 12,
|
45 |
+
"pooler_num_fc_layers": 3,
|
46 |
+
"pooler_size_per_head": 128,
|
47 |
+
"pooler_type": "first_token_transform",
|
48 |
+
"position_embedding_type": "absolute",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.16.2",
|
51 |
+
"type_vocab_size": 2,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 28996
|
54 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.6869693994522095
|
2 |
+
f1_score = 0.5537639511592938
|
3 |
+
f1_score_strict = 0.5685755336617406
|
4 |
+
precision = 0.5392645145552122
|
5 |
+
precision_strict = 0.6182350777637662
|
6 |
+
recall = 0.5764409020728622
|
7 |
+
recall_strict = 0.5448013164810617
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adam_epsilon": 1e-08, "best_model_dir": "temp/outputs/best_model", "cache_dir": "temp/cache_dir", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 1, "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": 10, "encoding": null, "eval_batch_size": 512, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 8, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 8, "manual_seed": 157, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "bert-large-cased", "model_type": "bert", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "output_dir": "temp/outputs", "overwrite_output_dir": true, "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_recent_only": true, "save_steps": 8, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": "ner", "warmup_ratio": 0.06, "warmup_steps": 12, "weight_decay": 0, "skip_special_tokens": true, "model_class": "NERModel", "classification_report": true, "labels_list": ["O", "B-quality", "B-property", "I-property", "I-quality", "B-object", "I-object", "B-value", "I-value"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddd737bae4784f598485ccef4a664a0c0f87b90f20a357e97f3006df2f1567c8
|
3 |
+
size 2660540357
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4a733e9f34187cf71791cbbde682a1119828a29458302f67ecac55b2627f337
|
3 |
+
size 1330319341
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66c919dc5e4fa90f825cb29c895ff6a66b2756374d342b10644020047cb54100
|
3 |
+
size 627
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/75be22d7750034989358861e325977feda47740e1c3f8a4dc1cb73570aad843e.2b9a196704f2f183fe3f4b48d6e662dba8203fdcb3346bfa896831378edf6f97", "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01ce7b49f5ded0d78c18bc82c73cd540507dac13a6fed8b54953f23d8df4f761
|
3 |
+
size 2491
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|