clejordan commited on
Commit
c71bc1e
·
verified ·
1 Parent(s): a5b6144

Delete checkpoint-5751/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-5751/trainer_state.json +0 -119
checkpoint-5751/trainer_state.json DELETED
@@ -1,119 +0,0 @@
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": 5751,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.0869414014953921,
14
- "grad_norm": NaN,
15
- "learning_rate": 0.00019421549875383993,
16
- "loss": 4.2823,
17
- "step": 500
18
- },
19
- {
20
- "epoch": 0.1738828029907842,
21
- "grad_norm": NaN,
22
- "learning_rate": 0.0001884194053208138,
23
- "loss": 0.0,
24
- "step": 1000
25
- },
26
- {
27
- "epoch": 0.2608242044861763,
28
- "grad_norm": NaN,
29
- "learning_rate": 0.00018262331188778763,
30
- "loss": 0.0,
31
- "step": 1500
32
- },
33
- {
34
- "epoch": 0.3477656059815684,
35
- "grad_norm": NaN,
36
- "learning_rate": 0.0001768272184547615,
37
- "loss": 0.0,
38
- "step": 2000
39
- },
40
- {
41
- "epoch": 0.4347070074769605,
42
- "grad_norm": NaN,
43
- "learning_rate": 0.00017103112502173535,
44
- "loss": 0.0,
45
- "step": 2500
46
- },
47
- {
48
- "epoch": 0.5216484089723527,
49
- "grad_norm": NaN,
50
- "learning_rate": 0.0001652350315887092,
51
- "loss": 0.0,
52
- "step": 3000
53
- },
54
- {
55
- "epoch": 0.6085898104677447,
56
- "grad_norm": NaN,
57
- "learning_rate": 0.00015943893815568308,
58
- "loss": 0.0,
59
- "step": 3500
60
- },
61
- {
62
- "epoch": 0.6955312119631368,
63
- "grad_norm": NaN,
64
- "learning_rate": 0.00015364284472265693,
65
- "loss": 0.0,
66
- "step": 4000
67
- },
68
- {
69
- "epoch": 0.7824726134585289,
70
- "grad_norm": NaN,
71
- "learning_rate": 0.0001478467512896308,
72
- "loss": 0.0,
73
- "step": 4500
74
- },
75
- {
76
- "epoch": 0.869414014953921,
77
- "grad_norm": NaN,
78
- "learning_rate": 0.00014205065785660465,
79
- "loss": 0.0,
80
- "step": 5000
81
- },
82
- {
83
- "epoch": 0.9563554164493132,
84
- "grad_norm": NaN,
85
- "learning_rate": 0.0001362545644235785,
86
- "loss": 0.0,
87
- "step": 5500
88
- },
89
- {
90
- "epoch": 1.0,
91
- "eval_loss": NaN,
92
- "eval_runtime": 152.5081,
93
- "eval_samples_per_second": 16.76,
94
- "eval_steps_per_second": 4.19,
95
- "step": 5751
96
- }
97
- ],
98
- "logging_steps": 500,
99
- "max_steps": 17253,
100
- "num_input_tokens_seen": 0,
101
- "num_train_epochs": 3,
102
- "save_steps": 500,
103
- "stateful_callbacks": {
104
- "TrainerControl": {
105
- "args": {
106
- "should_epoch_stop": false,
107
- "should_evaluate": false,
108
- "should_log": false,
109
- "should_save": true,
110
- "should_training_stop": false
111
- },
112
- "attributes": {}
113
- }
114
- },
115
- "total_flos": 3.115004127608832e+16,
116
- "train_batch_size": 4,
117
- "trial_name": null,
118
- "trial_params": null
119
- }