Matheus Matos Rocha commited on
Commit
d8f91ad
·
1 Parent(s): 7f722a9

Upload do modelo de Q&A

Browse files
config.json CHANGED
@@ -3,7 +3,6 @@
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
6
- "model_type": "bert",
7
  "attention_probs_dropout_prob": 0.1,
8
  "classifier_dropout": null,
9
  "directionality": "bidi",
@@ -15,6 +14,7 @@
15
  "intermediate_size": 3072,
16
  "layer_norm_eps": 1e-12,
17
  "max_position_embeddings": 512,
 
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "output_past": true,
 
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
 
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
  "directionality": "bidi",
 
14
  "intermediate_size": 3072,
15
  "layer_norm_eps": 1e-12,
16
  "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "output_past": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34f56535a11b50fcfcbb073c7510e37ff57417edf2ce835257bf690d947da5ec
3
  size 433359664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123818d2e0077aafee85e0568e79ab4d9815f69a408f096574f70295512189f3
3
  size 433359664
optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5e02a20b3bf0219113c56413813f47194cebc7e4c24ffedaef2f15b1282d1f
3
- size 866833530
 
 
 
 
rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aefd0179b98fc85cd30d19e03c1aa53d38723329dfde800d413bd5e9444df07
3
- size 13990
 
 
 
 
scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:912325317201a1f76547539b0ab54cd581e0c25c0b9ebbff0cd2f78ed8a1b53c
3
- size 1064
 
 
 
 
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 384,
6
+ "strategy": "OnlySecond",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 384
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
trainer_state.json DELETED
@@ -1,103 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.9850746268656714,
5
- "eval_steps": 500,
6
- "global_step": 501,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.29850746268656714,
13
- "grad_norm": 9.899151802062988,
14
- "learning_rate": 4.901960784313725e-05,
15
- "loss": 3.0988,
16
- "step": 50
17
- },
18
- {
19
- "epoch": 0.5970149253731343,
20
- "grad_norm": 4.365601062774658,
21
- "learning_rate": 4.4555555555555555e-05,
22
- "loss": 1.6841,
23
- "step": 100
24
- },
25
- {
26
- "epoch": 0.8955223880597015,
27
- "grad_norm": 6.207011699676514,
28
- "learning_rate": 3.9000000000000006e-05,
29
- "loss": 1.6733,
30
- "step": 150
31
- },
32
- {
33
- "epoch": 1.191044776119403,
34
- "grad_norm": 5.989271640777588,
35
- "learning_rate": 3.3444444444444443e-05,
36
- "loss": 1.5234,
37
- "step": 200
38
- },
39
- {
40
- "epoch": 1.48955223880597,
41
- "grad_norm": 5.798114776611328,
42
- "learning_rate": 2.788888888888889e-05,
43
- "loss": 1.4807,
44
- "step": 250
45
- },
46
- {
47
- "epoch": 1.7880597014925375,
48
- "grad_norm": 5.086219787597656,
49
- "learning_rate": 2.2333333333333335e-05,
50
- "loss": 1.4934,
51
- "step": 300
52
- },
53
- {
54
- "epoch": 2.083582089552239,
55
- "grad_norm": 9.068313598632812,
56
- "learning_rate": 1.677777777777778e-05,
57
- "loss": 1.4444,
58
- "step": 350
59
- },
60
- {
61
- "epoch": 2.382089552238806,
62
- "grad_norm": 7.573103904724121,
63
- "learning_rate": 1.1222222222222224e-05,
64
- "loss": 1.2715,
65
- "step": 400
66
- },
67
- {
68
- "epoch": 2.680597014925373,
69
- "grad_norm": 8.649182319641113,
70
- "learning_rate": 5.666666666666667e-06,
71
- "loss": 1.2803,
72
- "step": 450
73
- },
74
- {
75
- "epoch": 2.97910447761194,
76
- "grad_norm": 8.986006736755371,
77
- "learning_rate": 1.1111111111111112e-07,
78
- "loss": 1.2893,
79
- "step": 500
80
- }
81
- ],
82
- "logging_steps": 50,
83
- "max_steps": 501,
84
- "num_input_tokens_seen": 0,
85
- "num_train_epochs": 3,
86
- "save_steps": 500,
87
- "stateful_callbacks": {
88
- "TrainerControl": {
89
- "args": {
90
- "should_epoch_stop": false,
91
- "should_evaluate": false,
92
- "should_log": false,
93
- "should_save": true,
94
- "should_training_stop": true
95
- },
96
- "attributes": {}
97
- }
98
- },
99
- "total_flos": 1567388595280896.0,
100
- "train_batch_size": 4,
101
- "trial_name": null,
102
- "trial_params": null
103
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:14abf8755a247f484db8b73811aaace3bb041f9275cc68bf47f84a76ee79f0fe
3
- size 5304