QomSSLab commited on
Commit
5eeb28d
·
verified ·
1 Parent(s): 1b096a6

Add training logs and README

Browse files
Files changed (1) hide show
  1. trainer_state.json +97 -0
trainer_state.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0243617838745482,
6
+ "eval_steps": 500,
7
+ "global_step": 4500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11384011156330934,
14
+ "grad_norm": 3.0008609294891357,
15
+ "learning_rate": 4.999383491355718e-05,
16
+ "loss": 0.8935,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.22768022312661867,
21
+ "grad_norm": 0.27853482961654663,
22
+ "learning_rate": 4.944859128420597e-05,
23
+ "loss": 0.7408,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.341520334689928,
28
+ "grad_norm": 0.36637842655181885,
29
+ "learning_rate": 4.80398633245395e-05,
30
+ "loss": 0.7142,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.45536044625323735,
35
+ "grad_norm": 0.33963099122047424,
36
+ "learning_rate": 4.5817405006257364e-05,
37
+ "loss": 0.6999,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.5692005578165467,
42
+ "grad_norm": 0.31229811906814575,
43
+ "learning_rate": 4.28597099288601e-05,
44
+ "loss": 0.684,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.683040669379856,
49
+ "grad_norm": 0.3495138883590698,
50
+ "learning_rate": 3.92712390538606e-05,
51
+ "loss": 0.6902,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.7968807809431653,
56
+ "grad_norm": 0.2804907560348511,
57
+ "learning_rate": 3.517873131416236e-05,
58
+ "loss": 0.6559,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.9107208925064747,
63
+ "grad_norm": 0.28929612040519714,
64
+ "learning_rate": 3.072672740185862e-05,
65
+ "loss": 0.6455,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.0243617838745482,
70
+ "grad_norm": 0.36123162508010864,
71
+ "learning_rate": 2.607246482695919e-05,
72
+ "loss": 0.636,
73
+ "step": 4500
74
+ }
75
+ ],
76
+ "logging_steps": 500,
77
+ "max_steps": 8786,
78
+ "num_input_tokens_seen": 0,
79
+ "num_train_epochs": 2,
80
+ "save_steps": 250,
81
+ "stateful_callbacks": {
82
+ "TrainerControl": {
83
+ "args": {
84
+ "should_epoch_stop": false,
85
+ "should_evaluate": false,
86
+ "should_log": false,
87
+ "should_save": true,
88
+ "should_training_stop": false
89
+ },
90
+ "attributes": {}
91
+ }
92
+ },
93
+ "total_flos": 4.983938055942088e+18,
94
+ "train_batch_size": 1,
95
+ "trial_name": null,
96
+ "trial_params": null
97
+ }