Hugging Face's logo

phospho-ai
/
gr00t-replicate-PLB-simple-lego-pickup-mono-2-bw9euc2ha8

Safetensors
gr00t_n1
phosphobot
gr00t
replicate
Model card Files
xet
Community
PLB commited on
Commit
06b632a
·
verified ·
1 Parent(s): ab3f450

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": 0.2505175983436853,
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": 0.020703933747412008,
13
+ "grad_norm": 2.7109034061431885,
14
+ "learning_rate": 0.000199658449300667,
15
+ "loss": 0.5702,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.041407867494824016,
20
+ "grad_norm": 2.019132375717163,
21
+ "learning_rate": 0.0001936511241197055,
22
+ "loss": 0.2695,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.062111801242236024,
27
+ "grad_norm": 2.7597837448120117,
28
+ "learning_rate": 0.00018057651056609784,
29
+ "loss": 0.2096,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08281573498964803,
34
+ "grad_norm": 1.2507442235946655,
35
+ "learning_rate": 0.0001614212712689668,
36
+ "loss": 0.1855,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10351966873706005,
41
+ "grad_norm": 1.8468929529190063,
42
+ "learning_rate": 0.00013763093719478358,
43
+ "loss": 0.1573,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12422360248447205,
48
+ "grad_norm": 0.8407199382781982,
49
+ "learning_rate": 0.00011100082209940795,
50
+ "loss": 0.1637,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14492753623188406,
55
+ "grad_norm": 0.9125467538833618,
56
+ "learning_rate": 8.35405409719266e-05,
57
+ "loss": 0.1278,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.16563146997929606,
62
+ "grad_norm": 0.8212506175041199,
63
+ "learning_rate": 5.732235645035964e-05,
64
+ "loss": 0.1175,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18633540372670807,
69
+ "grad_norm": 0.6263362169265747,
70
+ "learning_rate": 3.4324797595226565e-05,
71
+ "loss": 0.1032,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2070393374741201,
76
+ "grad_norm": 0.6752850413322449,
77
+ "learning_rate": 1.6283352173747145e-05,
78
+ "loss": 0.1003,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2277432712215321,
83
+ "grad_norm": 0.7334072589874268,
84
+ "learning_rate": 4.559499812049251e-06,
85
+ "loss": 0.0935,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2484472049689441,
90
+ "grad_norm": 0.4544273614883423,
91
+ "learning_rate": 3.796929750485845e-08,
92
+ "loss": 0.1022,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2505175983436853,
97
+ "step": 121,
98
+ "total_flos": 4388878621315584.0,
99
+ "train_loss": 0.18267044973028593,
100
+ "train_runtime": 73.0167,
101
+ "train_samples_per_second": 26.514,
102
+ "train_steps_per_second": 1.657
103
+ }
104
+ ],
105
+ "logging_steps": 10,
106
+ "max_steps": 121,
107
+ "num_input_tokens_seen": 0,
108
+ "num_train_epochs": 1,
109
+ "save_steps": 500,
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": 4388878621315584.0,
123
+ "train_batch_size": 16,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }