ybkim95-ai commited on
Commit
156ad4d
·
verified ·
1 Parent(s): fd84290

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +100 -0
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.8095238095238093,
5
+ "eval_steps": 500,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.38095238095238093,
13
+ "grad_norm": 128.80056652631617,
14
+ "learning_rate": 0.0001,
15
+ "loss": 1.939,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.7619047619047619,
20
+ "grad_norm": 128.356467747052,
21
+ "learning_rate": 9.698463103929542e-05,
22
+ "loss": 1.9333,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 1.1428571428571428,
27
+ "grad_norm": 360.8624759690317,
28
+ "learning_rate": 8.83022221559489e-05,
29
+ "loss": 9.7012,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 1.5238095238095237,
34
+ "grad_norm": 123.43648733761829,
35
+ "learning_rate": 7.500000000000001e-05,
36
+ "loss": 3.0347,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 1.9047619047619047,
41
+ "grad_norm": 269.2858901335159,
42
+ "learning_rate": 5.868240888334653e-05,
43
+ "loss": 5.0547,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 2.2857142857142856,
48
+ "grad_norm": 26.38091309419736,
49
+ "learning_rate": 4.131759111665349e-05,
50
+ "loss": 0.7275,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 2.6666666666666665,
55
+ "grad_norm": 25.39288571666346,
56
+ "learning_rate": 2.500000000000001e-05,
57
+ "loss": 0.9666,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 3.0476190476190474,
62
+ "grad_norm": 10.098295434315187,
63
+ "learning_rate": 1.1697777844051105e-05,
64
+ "loss": 0.3615,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 3.4285714285714284,
69
+ "grad_norm": 11.223311238174132,
70
+ "learning_rate": 3.0153689607045845e-06,
71
+ "loss": 0.2268,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 3.8095238095238093,
76
+ "grad_norm": 4.0409752690257745,
77
+ "learning_rate": 0.0,
78
+ "loss": 0.0909,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 3.8095238095238093,
83
+ "step": 10,
84
+ "total_flos": 5.956250982416384e+16,
85
+ "train_loss": 2.4036094665527346,
86
+ "train_runtime": 166.6494,
87
+ "train_samples_per_second": 4.981,
88
+ "train_steps_per_second": 0.06
89
+ }
90
+ ],
91
+ "logging_steps": 1.0,
92
+ "max_steps": 10,
93
+ "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 5,
95
+ "save_steps": 500,
96
+ "total_flos": 5.956250982416384e+16,
97
+ "train_batch_size": 2,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }