Hugging Face's logo

PLB
/
debug-hihi

Safetensors
gr00t_n1
phosphobot
gr00t
Model card Files
xet
Community
PLB commited on
Commit
f1add34
·
verified ·
1 Parent(s): 9e37892

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +168 -0
trainer_state.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 185,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05405405405405406,
13
+ "grad_norm": 1.8533293008804321,
14
+ "learning_rate": 0.0001,
15
+ "loss": 0.7553,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.10810810810810811,
20
+ "grad_norm": 1.8566731214523315,
21
+ "learning_rate": 9.919647942993148e-05,
22
+ "loss": 0.2456,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.16216216216216217,
27
+ "grad_norm": 1.426089882850647,
28
+ "learning_rate": 9.681174353198687e-05,
29
+ "loss": 0.1699,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.21621621621621623,
34
+ "grad_norm": 0.7362193465232849,
35
+ "learning_rate": 9.292243968009331e-05,
36
+ "loss": 0.1341,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2702702702702703,
41
+ "grad_norm": 1.2846084833145142,
42
+ "learning_rate": 8.765357330018056e-05,
43
+ "loss": 0.1093,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.32432432432432434,
48
+ "grad_norm": 0.5028020739555359,
49
+ "learning_rate": 8.117449009293668e-05,
50
+ "loss": 0.106,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.3783783783783784,
55
+ "grad_norm": 1.2113736867904663,
56
+ "learning_rate": 7.369343312364993e-05,
57
+ "loss": 0.0977,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.43243243243243246,
62
+ "grad_norm": 0.6515302658081055,
63
+ "learning_rate": 6.545084971874738e-05,
64
+ "loss": 0.0861,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.4864864864864865,
69
+ "grad_norm": 0.5156140923500061,
70
+ "learning_rate": 5.6711663290882776e-05,
71
+ "loss": 0.0856,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.5405405405405406,
76
+ "grad_norm": 0.4655522108078003,
77
+ "learning_rate": 4.775675848247427e-05,
78
+ "loss": 0.065,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.5945945945945946,
83
+ "grad_norm": 0.6544004678726196,
84
+ "learning_rate": 3.887395330218429e-05,
85
+ "loss": 0.0742,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.6486486486486487,
90
+ "grad_norm": 0.5006158947944641,
91
+ "learning_rate": 3.0348748417303823e-05,
92
+ "loss": 0.0641,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.7027027027027027,
97
+ "grad_norm": 0.4036032259464264,
98
+ "learning_rate": 2.245515092739488e-05,
99
+ "loss": 0.0562,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.7567567567567568,
104
+ "grad_norm": 0.6734123229980469,
105
+ "learning_rate": 1.544686755065677e-05,
106
+ "loss": 0.0609,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.8108108108108109,
111
+ "grad_norm": 0.7298457622528076,
112
+ "learning_rate": 9.549150281252633e-06,
113
+ "loss": 0.065,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.8648648648648649,
118
+ "grad_norm": 0.47052305936813354,
119
+ "learning_rate": 4.951556604879048e-06,
120
+ "loss": 0.0577,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.918918918918919,
125
+ "grad_norm": 0.46818605065345764,
126
+ "learning_rate": 1.8018569652073381e-06,
127
+ "loss": 0.0547,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.972972972972973,
132
+ "grad_norm": 0.6747378706932068,
133
+ "learning_rate": 2.012853002380466e-07,
134
+ "loss": 0.0502,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.0,
139
+ "step": 185,
140
+ "total_flos": 2.671639181415504e+16,
141
+ "train_loss": 0.12806547799625911,
142
+ "train_runtime": 362.2784,
143
+ "train_samples_per_second": 32.53,
144
+ "train_steps_per_second": 0.511
145
+ }
146
+ ],
147
+ "logging_steps": 10,
148
+ "max_steps": 185,
149
+ "num_input_tokens_seen": 0,
150
+ "num_train_epochs": 1,
151
+ "save_steps": 10000,
152
+ "stateful_callbacks": {
153
+ "TrainerControl": {
154
+ "args": {
155
+ "should_epoch_stop": false,
156
+ "should_evaluate": false,
157
+ "should_log": false,
158
+ "should_save": true,
159
+ "should_training_stop": true
160
+ },
161
+ "attributes": {}
162
+ }
163
+ },
164
+ "total_flos": 2.671639181415504e+16,
165
+ "train_batch_size": 64,
166
+ "trial_name": null,
167
+ "trial_params": null
168
+ }