PLB commited on
Commit
19e18c5
·
verified ·
1 Parent(s): 05d34fe

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +126 -0
trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 121,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08264462809917356,
13
+ "grad_norm": 7.750270843505859,
14
+ "learning_rate": 0.000199658449300667,
15
+ "loss": 0.5852,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.1652892561983471,
20
+ "grad_norm": 23.40735626220703,
21
+ "learning_rate": 0.0001936511241197055,
22
+ "loss": 0.3072,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.24793388429752067,
27
+ "grad_norm": 24.60139274597168,
28
+ "learning_rate": 0.00018057651056609784,
29
+ "loss": 0.2754,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.3305785123966942,
34
+ "grad_norm": 0.9646787047386169,
35
+ "learning_rate": 0.0001614212712689668,
36
+ "loss": 0.1879,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.4132231404958678,
41
+ "grad_norm": 0.9788209199905396,
42
+ "learning_rate": 0.00013763093719478358,
43
+ "loss": 0.1493,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.49586776859504134,
48
+ "grad_norm": 0.7880584597587585,
49
+ "learning_rate": 0.00011100082209940795,
50
+ "loss": 0.1321,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.5785123966942148,
55
+ "grad_norm": 0.5986640453338623,
56
+ "learning_rate": 8.35405409719266e-05,
57
+ "loss": 0.1109,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.6611570247933884,
62
+ "grad_norm": 0.9021563529968262,
63
+ "learning_rate": 5.732235645035964e-05,
64
+ "loss": 0.1011,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.743801652892562,
69
+ "grad_norm": 0.5953593254089355,
70
+ "learning_rate": 3.4324797595226565e-05,
71
+ "loss": 0.0918,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.8264462809917356,
76
+ "grad_norm": 0.3122101128101349,
77
+ "learning_rate": 1.6283352173747145e-05,
78
+ "loss": 0.0749,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.9090909090909091,
83
+ "grad_norm": 0.42104968428611755,
84
+ "learning_rate": 4.559499812049251e-06,
85
+ "loss": 0.0831,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.9917355371900827,
90
+ "grad_norm": 0.40868669748306274,
91
+ "learning_rate": 3.796929750485845e-08,
92
+ "loss": 0.0733,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "step": 121,
98
+ "total_flos": 1.7516975778360288e+16,
99
+ "train_loss": 0.1801821660281213,
100
+ "train_runtime": 186.5904,
101
+ "train_samples_per_second": 41.412,
102
+ "train_steps_per_second": 0.648
103
+ }
104
+ ],
105
+ "logging_steps": 10,
106
+ "max_steps": 121,
107
+ "num_input_tokens_seen": 0,
108
+ "num_train_epochs": 1,
109
+ "save_steps": 10000,
110
+ "stateful_callbacks": {
111
+ "TrainerControl": {
112
+ "args": {
113
+ "should_epoch_stop": false,
114
+ "should_evaluate": false,
115
+ "should_log": false,
116
+ "should_save": true,
117
+ "should_training_stop": true
118
+ },
119
+ "attributes": {}
120
+ }
121
+ },
122
+ "total_flos": 1.7516975778360288e+16,
123
+ "train_batch_size": 64,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }