tmnam20 commited on
Commit
92c497d
1 Parent(s): fd5f9d0

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +97 -0
trainer_state.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 522,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.29,
13
+ "learning_rate": 1.8084291187739463e-05,
14
+ "loss": 1.7677,
15
+ "step": 50
16
+ },
17
+ {
18
+ "epoch": 0.57,
19
+ "learning_rate": 1.6168582375478928e-05,
20
+ "loss": 1.6459,
21
+ "step": 100
22
+ },
23
+ {
24
+ "epoch": 0.86,
25
+ "learning_rate": 1.4252873563218392e-05,
26
+ "loss": 1.5382,
27
+ "step": 150
28
+ },
29
+ {
30
+ "epoch": 1.15,
31
+ "learning_rate": 1.2337164750957855e-05,
32
+ "loss": 1.4074,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 1.44,
37
+ "learning_rate": 1.0421455938697318e-05,
38
+ "loss": 1.3047,
39
+ "step": 250
40
+ },
41
+ {
42
+ "epoch": 1.72,
43
+ "learning_rate": 8.505747126436782e-06,
44
+ "loss": 1.2752,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 2.01,
49
+ "learning_rate": 6.590038314176246e-06,
50
+ "loss": 1.2642,
51
+ "step": 350
52
+ },
53
+ {
54
+ "epoch": 2.3,
55
+ "learning_rate": 4.674329501915709e-06,
56
+ "loss": 1.1416,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 2.59,
61
+ "learning_rate": 2.7586206896551725e-06,
62
+ "loss": 1.1195,
63
+ "step": 450
64
+ },
65
+ {
66
+ "epoch": 2.87,
67
+ "learning_rate": 8.429118773946361e-07,
68
+ "loss": 1.0403,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 2.87,
73
+ "eval_accuracy": 0.5335276967930029,
74
+ "eval_loss": 1.332867980003357,
75
+ "eval_runtime": 0.5841,
76
+ "eval_samples_per_second": 1174.52,
77
+ "eval_steps_per_second": 73.622,
78
+ "step": 500
79
+ },
80
+ {
81
+ "epoch": 3.0,
82
+ "step": 522,
83
+ "total_flos": 513940629063600.0,
84
+ "train_loss": 1.339250513420251,
85
+ "train_runtime": 70.1753,
86
+ "train_samples_per_second": 237.177,
87
+ "train_steps_per_second": 7.439
88
+ }
89
+ ],
90
+ "logging_steps": 50,
91
+ "max_steps": 522,
92
+ "num_train_epochs": 3,
93
+ "save_steps": 500,
94
+ "total_flos": 513940629063600.0,
95
+ "trial_name": null,
96
+ "trial_params": null
97
+ }