tomhaishiwo commited on
Commit
94172d4
·
1 Parent(s): 8696041

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "snowood1/ConfliBERT-scr-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "Non",
14
+ "1": "Conflict"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Conflict": 1,
20
+ "Non": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.33.1",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30000
35
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252bb98b2599a9e421e8c0b81ee6c873c1abeac5f919160c862eb7d16fbb1484
3
+ size 872830725
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820a9fa15979b94c5eaf89fb3b1d15f44476c9db36ffe15a3c235da703332804
3
+ size 436399921
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1b94df60a8ff1bb330dcabf6942eb97bd8d1ea3d1ce827f9dc2a67c2cffca5
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9408e7fb9501740bc453b1cfc37c7585fe2a326cc9b6a3cd48f7930f9c6a66de
3
+ size 627
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.17575937509536743,
3
+ "best_model_checkpoint": "./outputs/model\\checkpoint-1102",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1102,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.91,
13
+ "learning_rate": 1.0925589836660618e-05,
14
+ "loss": 0.1892,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.941916085827525,
20
+ "eval_loss": 0.2061644345521927,
21
+ "eval_runtime": 52.2792,
22
+ "eval_samples_per_second": 139.96,
23
+ "eval_steps_per_second": 8.761,
24
+ "step": 551
25
+ },
26
+ {
27
+ "epoch": 1.81,
28
+ "learning_rate": 1.8511796733212343e-06,
29
+ "loss": 0.1121,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.947246139128058,
35
+ "eval_loss": 0.17575937509536743,
36
+ "eval_runtime": 52.3043,
37
+ "eval_samples_per_second": 139.893,
38
+ "eval_steps_per_second": 8.756,
39
+ "step": 1102
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1102,
44
+ "num_train_epochs": 2,
45
+ "save_steps": 500,
46
+ "total_flos": 4409930398904640.0,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd120cc4bae515923b96b5d3ff6586eec52261fe3d96750e6c763a9210fcde32
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff