p3ngdump commited on
Commit
00f5a86
1 Parent(s): fb98ab2

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./kcbert-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 300,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "problem_type": "single_label_classification",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.40.0.dev0",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30000
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7218fce2325bf66b4584af966a66f9de2e65d38746b4e1bcdf5fb301a40af131
3
+ size 435731846
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1da4cf1a8fc2882fa2977afac1a0db3c90f3280ea49f706c1b1b7966aab6600
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab259b434483e0b46e40b45a81e777ee6ee5b295060a60e20426cd438ac9dff
3
+ size 1064
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 300,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.888268156424581,
5
+ "eval_steps": 500,
6
+ "global_step": 3500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7,
13
+ "grad_norm": 6.08462381362915,
14
+ "learning_rate": 1.7206703910614527e-05,
15
+ "loss": 0.3865,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.4,
20
+ "grad_norm": 5.282430648803711,
21
+ "learning_rate": 1.4413407821229052e-05,
22
+ "loss": 0.2899,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.09,
27
+ "grad_norm": 4.065394878387451,
28
+ "learning_rate": 1.1620111731843577e-05,
29
+ "loss": 0.2214,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.79,
34
+ "grad_norm": 8.418371200561523,
35
+ "learning_rate": 8.826815642458101e-06,
36
+ "loss": 0.1093,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.49,
41
+ "grad_norm": 20.9011173248291,
42
+ "learning_rate": 6.033519553072626e-06,
43
+ "loss": 0.0653,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 4.19,
48
+ "grad_norm": 4.803398132324219,
49
+ "learning_rate": 3.240223463687151e-06,
50
+ "loss": 0.0406,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 4.89,
55
+ "grad_norm": 0.0067610470578074455,
56
+ "learning_rate": 4.46927374301676e-07,
57
+ "loss": 0.0164,
58
+ "step": 3500
59
+ }
60
+ ],
61
+ "logging_steps": 500,
62
+ "max_steps": 3580,
63
+ "num_input_tokens_seen": 0,
64
+ "num_train_epochs": 5,
65
+ "save_steps": 500,
66
+ "total_flos": 3179834312329860.0,
67
+ "train_batch_size": 32,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5eb65ac24cf26630d6e56787a90d11d4fe7f69e85cbffbeb3c17bd83cf982c
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff