Commit
•
aa388b3
1
Parent(s):
dcdac36
best model for qa
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +94 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/projects/SolarWindowsADSP/shu/models/bert-base-cased/",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
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 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.17.0.dev0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 28996
|
26 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73b89345bde715153dd3aabb21ac41112de25fe10796a29357f84c61adf1b357
|
3 |
+
size 861894637
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d889c4a1e2018c2400fbb4facef2470becbfa230163aa2f03eb4a337f01853
|
3 |
+
size 430973431
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e52c4dc9f0b6027861d9f82533bfa75552e49459a52af747f965b9a3e173d1
|
3 |
+
size 14657
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f0590c7cc50662a1d524c6e2e05d15f088f80aa6f638eebf6d05611e53f7241
|
3 |
+
size 14657
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72f978760997b87af8e24f87ce24f24353a6454ad7b2b368ef601d3adb13ddcf
|
3 |
+
size 14657
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fdd13f7e6c0bdc70fe28b406d558e13924f29022fe182c6dc451c3227e60bbb
|
3 |
+
size 14657
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4589a3500937edd1bf434bd7c9059e931792c96922065277779a10a295ec5b8
|
3 |
+
size 14657
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5146c979f432c7fdcff56f197d333de5fea21e202dd9f47d1d92d84f5ed944c
|
3 |
+
size 14657
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8659629f68899fff8ea73907f316f7c58a7426b3593eac457f160208d9e64a23
|
3 |
+
size 14657
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78fd75e0aa8e02bf3cbef338768a2e39cc1feb146e4d9497b1d76a5294789e40
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f069092755d43f4443a85925a4bd11e00e6f0af33e6dbf8088b6343672afce0
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/projects/SolarWindowsADSP/shu/models/bert-base-cased/", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 5546,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.18,
|
12 |
+
"learning_rate": 4.774612333213127e-05,
|
13 |
+
"loss": 1.7894,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.36,
|
18 |
+
"learning_rate": 4.549224666426253e-05,
|
19 |
+
"loss": 1.2681,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.54,
|
24 |
+
"learning_rate": 4.32383699963938e-05,
|
25 |
+
"loss": 1.1511,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.72,
|
30 |
+
"learning_rate": 4.0984493328525064e-05,
|
31 |
+
"loss": 1.1003,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.9,
|
36 |
+
"learning_rate": 3.873061666065633e-05,
|
37 |
+
"loss": 1.0589,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"eval_exact_match": 79.72563859981078,
|
43 |
+
"eval_f1": 87.33897800522966,
|
44 |
+
"step": 2773
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.08,
|
48 |
+
"learning_rate": 3.6476739992787594e-05,
|
49 |
+
"loss": 0.8936,
|
50 |
+
"step": 3000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.26,
|
54 |
+
"learning_rate": 3.422286332491886e-05,
|
55 |
+
"loss": 0.7398,
|
56 |
+
"step": 3500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.44,
|
60 |
+
"learning_rate": 3.1968986657050125e-05,
|
61 |
+
"loss": 0.738,
|
62 |
+
"step": 4000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.62,
|
66 |
+
"learning_rate": 2.9715109989181394e-05,
|
67 |
+
"loss": 0.7341,
|
68 |
+
"step": 4500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.8,
|
72 |
+
"learning_rate": 2.7461233321312656e-05,
|
73 |
+
"loss": 0.7264,
|
74 |
+
"step": 5000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.98,
|
78 |
+
"learning_rate": 2.5207356653443925e-05,
|
79 |
+
"loss": 0.728,
|
80 |
+
"step": 5500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.0,
|
84 |
+
"eval_exact_match": 81.2961210974456,
|
85 |
+
"eval_f1": 88.57827007260809,
|
86 |
+
"step": 5546
|
87 |
+
}
|
88 |
+
],
|
89 |
+
"max_steps": 11092,
|
90 |
+
"num_train_epochs": 4,
|
91 |
+
"total_flos": 3.4779642825015296e+16,
|
92 |
+
"trial_name": null,
|
93 |
+
"trial_params": null
|
94 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce5da6709f1e587806932d8b6a58f9aba97649f9be714b914efbf3c6530007a
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|