princeton-nlp commited on
Commit
d8db020
1 Parent(s): 19d02e7

Upload 9 files

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMabel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.2.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
log.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd7560727c03ed61a388a68b1cd4424029dd59b0da2422ffb0dd0476648e2d9
3
+ size 1340856491
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": true, "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, "name_or_path": "bert-large-uncased"}
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 5721.0485
3
+ train_samples_per_second = 0.583
trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 3333,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.45,
12
+ "learning_rate": 2.5499549954995502e-05,
13
+ "loss": 3.7031,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.9,
18
+ "learning_rate": 2.0999099909991e-05,
19
+ "loss": 2.1276,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.35,
24
+ "learning_rate": 1.64986498649865e-05,
25
+ "loss": 1.8363,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.8,
30
+ "learning_rate": 1.1998199819981998e-05,
31
+ "loss": 1.6986,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.25,
36
+ "learning_rate": 7.497749774977498e-06,
37
+ "loss": 1.6041,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 2.7,
42
+ "learning_rate": 2.997299729972997e-06,
43
+ "loss": 1.5504,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "step": 3333,
49
+ "train_runtime": 5721.0485,
50
+ "train_samples_per_second": 0.583
51
+ }
52
+ ],
53
+ "max_steps": 3333,
54
+ "num_train_epochs": 3,
55
+ "total_flos": 633709039885608960,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d759a308a1603f375d0fd196e494d542589cd5ac0a7560e2ee9437a4da058c
3
+ size 2095
vocab.txt ADDED
The diff for this file is too large to render. See raw diff