dyllanesl commited on
Commit
75485d9
·
verified ·
1 Parent(s): 02d5ec9

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +68 -4
trainer_state.json CHANGED
@@ -3,13 +3,77 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
- "log_history": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "logging_steps": 10,
12
- "max_steps": 6,
13
  "num_input_tokens_seen": 0,
14
  "num_train_epochs": 3,
15
  "save_steps": 500,
@@ -25,7 +89,7 @@
25
  "attributes": {}
26
  }
27
  },
28
- "total_flos": 4417914356416512.0,
29
  "train_batch_size": 16,
30
  "trial_name": null,
31
  "trial_params": null
 
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.30303030303030304,
13
+ "grad_norm": 8.750067710876465,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 3.3586,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.6060606060606061,
20
+ "grad_norm": 9.16357421875,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 3.332,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.9090909090909091,
27
+ "grad_norm": 8.869489669799805,
28
+ "learning_rate": 3e-06,
29
+ "loss": 3.3107,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 1.2121212121212122,
34
+ "grad_norm": 8.31998348236084,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 3.2271,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.5151515151515151,
41
+ "grad_norm": 8.316051483154297,
42
+ "learning_rate": 5e-06,
43
+ "loss": 3.0808,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.8181818181818183,
48
+ "grad_norm": 8.299915313720703,
49
+ "learning_rate": 6e-06,
50
+ "loss": 3.0593,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 2.121212121212121,
55
+ "grad_norm": 7.488762855529785,
56
+ "learning_rate": 7.000000000000001e-06,
57
+ "loss": 2.8781,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 2.4242424242424243,
62
+ "grad_norm": 8.20336627960205,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 2.731,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 2.7272727272727275,
69
+ "grad_norm": 9.079769134521484,
70
+ "learning_rate": 9e-06,
71
+ "loss": 2.5706,
72
+ "step": 90
73
+ }
74
+ ],
75
  "logging_steps": 10,
76
+ "max_steps": 99,
77
  "num_input_tokens_seen": 0,
78
  "num_train_epochs": 3,
79
  "save_steps": 500,
 
89
  "attributes": {}
90
  }
91
  },
92
+ "total_flos": 1.20913507233792e+17,
93
  "train_batch_size": 16,
94
  "trial_name": null,
95
  "trial_params": null