update from clhuang
Browse files- optimizer.pt +0 -3
- rng_state.pth +0 -3
- scheduler.pt +0 -3
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +0 -82
- training_args.bin +0 -3
- vocab.txt +0 -0
optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:09f484ecf330695cf604ab9c5ab2ae7161156d9423cc36c594fd92334287e322
|
3 |
-
size 84466563
|
|
|
|
|
|
|
|
rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:cfbafeb8298acbb83505265c84391943881508a522717de6681e875a516d7cdb
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a40ef085858cb95701334037a0232e17223889497e5e8d68b6d06c5b178967bb
|
3 |
-
size 623
|
|
|
|
|
|
|
|
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, "name_or_path": "bert-base-chinese", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
DELETED
@@ -1,82 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.2616243362426758,
|
3 |
-
"best_model_checkpoint": "./checkpoints/checkpoint-1964",
|
4 |
-
"epoch": 4.0,
|
5 |
-
"global_step": 1964,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 1.0,
|
12 |
-
"eval_accuracy": 0.8884644766997708,
|
13 |
-
"eval_f1": 0.8884644766997708,
|
14 |
-
"eval_loss": 0.4412623643875122,
|
15 |
-
"eval_precision": 0.8884644766997708,
|
16 |
-
"eval_recall": 0.8884644766997708,
|
17 |
-
"eval_runtime": 43.6404,
|
18 |
-
"eval_samples_per_second": 59.99,
|
19 |
-
"eval_steps_per_second": 1.879,
|
20 |
-
"step": 491
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 1.02,
|
24 |
-
"learning_rate": 2e-05,
|
25 |
-
"loss": 1.3111,
|
26 |
-
"step": 500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 2.0,
|
30 |
-
"eval_accuracy": 0.9037433155080213,
|
31 |
-
"eval_f1": 0.9037433155080212,
|
32 |
-
"eval_loss": 0.31344300508499146,
|
33 |
-
"eval_precision": 0.9037433155080213,
|
34 |
-
"eval_recall": 0.9037433155080213,
|
35 |
-
"eval_runtime": 43.7135,
|
36 |
-
"eval_samples_per_second": 59.89,
|
37 |
-
"eval_steps_per_second": 1.876,
|
38 |
-
"step": 982
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 2.04,
|
42 |
-
"learning_rate": 1.591169255928046e-05,
|
43 |
-
"loss": 0.3547,
|
44 |
-
"step": 1000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 3.0,
|
48 |
-
"eval_accuracy": 0.9113827349121467,
|
49 |
-
"eval_f1": 0.9113827349121467,
|
50 |
-
"eval_loss": 0.2822723388671875,
|
51 |
-
"eval_precision": 0.9113827349121467,
|
52 |
-
"eval_recall": 0.9113827349121467,
|
53 |
-
"eval_runtime": 43.7763,
|
54 |
-
"eval_samples_per_second": 59.804,
|
55 |
-
"eval_steps_per_second": 1.873,
|
56 |
-
"step": 1473
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 3.05,
|
60 |
-
"learning_rate": 1.1823385118560918e-05,
|
61 |
-
"loss": 0.2375,
|
62 |
-
"step": 1500
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 4.0,
|
66 |
-
"eval_accuracy": 0.9182582123758595,
|
67 |
-
"eval_f1": 0.9182582123758595,
|
68 |
-
"eval_loss": 0.2616243362426758,
|
69 |
-
"eval_precision": 0.9182582123758595,
|
70 |
-
"eval_recall": 0.9182582123758595,
|
71 |
-
"eval_runtime": 43.7951,
|
72 |
-
"eval_samples_per_second": 59.778,
|
73 |
-
"eval_steps_per_second": 1.872,
|
74 |
-
"step": 1964
|
75 |
-
}
|
76 |
-
],
|
77 |
-
"max_steps": 2946,
|
78 |
-
"num_train_epochs": 6,
|
79 |
-
"total_flos": 1100711158866000.0,
|
80 |
-
"trial_name": null,
|
81 |
-
"trial_params": null
|
82 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:de0b1abc9b0f344d42c820704816e67924b2521c28a82621417365ae1e1662de
|
3 |
-
size 3183
|
|
|
|
|
|
|
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|