Prahaladha commited on
Commit
7e578a0
·
verified ·
1 Parent(s): 9919667

Upload phaseB_medium/checkpoint-154/trainer_state.json with huggingface_hub

Browse files
phaseB_medium/checkpoint-154/trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 154,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06527947776417789,
14
+ "grad_norm": 0.3659420311450958,
15
+ "learning_rate": 4.999421254949728e-05,
16
+ "loss": 0.5493,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.13055895552835578,
21
+ "grad_norm": 0.3503095209598541,
22
+ "learning_rate": 4.930295491572653e-05,
23
+ "loss": 0.5735,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.19583843329253367,
28
+ "grad_norm": 0.42860716581344604,
29
+ "learning_rate": 4.749077174130608e-05,
30
+ "loss": 0.5553,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.26111791105671156,
35
+ "grad_norm": 0.4349290430545807,
36
+ "learning_rate": 4.464124637696786e-05,
37
+ "loss": 0.5709,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.3263973888208894,
42
+ "grad_norm": 0.4874759018421173,
43
+ "learning_rate": 4.088580752225444e-05,
44
+ "loss": 0.5424,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.39167686658506734,
49
+ "grad_norm": 0.39663174748420715,
50
+ "learning_rate": 3.639766733771147e-05,
51
+ "loss": 0.5106,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.4569563443492452,
56
+ "grad_norm": 0.3940886855125427,
57
+ "learning_rate": 3.1383832377904675e-05,
58
+ "loss": 0.5367,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.5222358221134231,
63
+ "grad_norm": 0.4165942966938019,
64
+ "learning_rate": 2.607555582511326e-05,
65
+ "loss": 0.5536,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.587515299877601,
70
+ "grad_norm": 0.37471580505371094,
71
+ "learning_rate": 2.071767139546306e-05,
72
+ "loss": 0.5372,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.6527947776417788,
77
+ "grad_norm": 0.37760552763938904,
78
+ "learning_rate": 1.5557300869900876e-05,
79
+ "loss": 0.5255,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.7180742554059567,
84
+ "grad_norm": 0.3830636143684387,
85
+ "learning_rate": 1.0832456092722062e-05,
86
+ "loss": 0.5326,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.7833537331701347,
91
+ "grad_norm": 0.3630097210407257,
92
+ "learning_rate": 6.761061147837808e-06,
93
+ "loss": 0.5391,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.8486332109343125,
98
+ "grad_norm": 0.4070269465446472,
99
+ "learning_rate": 3.5309010431049283e-06,
100
+ "loss": 0.5158,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.9139126886984904,
105
+ "grad_norm": 0.3441726267337799,
106
+ "learning_rate": 1.2909604996957092e-06,
107
+ "loss": 0.5276,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.9791921664626683,
112
+ "grad_norm": 0.34463751316070557,
113
+ "learning_rate": 1.4455232765120396e-07,
114
+ "loss": 0.5374,
115
+ "step": 150
116
+ }
117
+ ],
118
+ "logging_steps": 10,
119
+ "max_steps": 154,
120
+ "num_input_tokens_seen": 0,
121
+ "num_train_epochs": 1,
122
+ "save_steps": 200,
123
+ "stateful_callbacks": {
124
+ "TrainerControl": {
125
+ "args": {
126
+ "should_epoch_stop": false,
127
+ "should_evaluate": false,
128
+ "should_log": false,
129
+ "should_save": true,
130
+ "should_training_stop": true
131
+ },
132
+ "attributes": {}
133
+ }
134
+ },
135
+ "total_flos": 5.526035444970086e+16,
136
+ "train_batch_size": 1,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }