Ghaith Dekhili commited on
Commit
d71951e
1 Parent(s): b3e32f3

third commit

Browse files
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01ab7201c7c6363575b5d0633140a78d6b82f84681545ce2c87b743e2affd16
3
+ size 875930250
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1391fa76ef24df22c1790489251d0822417f940c41d9b1bdfde26c242dd86d
3
+ size 437989677
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7bc19bedf4abd7e2bfb21ba74cb45e7909ffaeefca3cb21be583cf7ff653a1
3
+ size 326
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-base-uncased"}
trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9426312247644684,
3
+ "best_model_checkpoint": "cq-bert-model-repo/checkpoint-3042",
4
+ "epoch": 1.0,
5
+ "global_step": 3042,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16436554898093358,
12
+ "learning_rate": 1.671268902038133e-05,
13
+ "loss": 0.2786270751953125,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.32873109796186717,
18
+ "learning_rate": 1.3425378040762658e-05,
19
+ "loss": 0.24325125122070312,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.4930966469428008,
24
+ "learning_rate": 1.0138067061143987e-05,
25
+ "loss": 0.21087245178222655,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.6574621959237343,
30
+ "learning_rate": 6.850756081525313e-06,
31
+ "loss": 0.19398100280761718,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.821827744904668,
36
+ "learning_rate": 3.563445101906641e-06,
37
+ "loss": 0.20912657165527343,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.9861932938856016,
42
+ "learning_rate": 2.7613412228796843e-07,
43
+ "loss": 0.19943014526367187,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.9426312247644684,
49
+ "eval_f1": 0.8816383200277681,
50
+ "eval_loss": 0.18397130072116852,
51
+ "step": 3042
52
+ }
53
+ ],
54
+ "max_steps": 3042,
55
+ "num_train_epochs": 1,
56
+ "total_flos": 1321583063589120,
57
+ "trial_name": null,
58
+ "trial_params": null
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46104c1ab0ae348ceae93b57ad5b5782e104bb6ab59370beb6de0ebd254c3a4d
3
+ size 1640
vocab.txt ADDED
The diff for this file is too large to render. See raw diff