byesher commited on
Commit
09de4ac
·
verified ·
1 Parent(s): 133bff6

Delete checkpoint-148/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-148/trainer_state.json +0 -131
checkpoint-148/trainer_state.json DELETED
@@ -1,131 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.9983136593591906,
5
- "eval_steps": 500,
6
- "global_step": 148,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.06745362563237774,
13
- "grad_norm": 0.5758384466171265,
14
- "learning_rate": 9.994965332706573e-05,
15
- "loss": 1.2053,
16
- "step": 10
17
- },
18
- {
19
- "epoch": 0.13490725126475547,
20
- "grad_norm": 0.3025762438774109,
21
- "learning_rate": 9.819814303479267e-05,
22
- "loss": 0.9519,
23
- "step": 20
24
- },
25
- {
26
- "epoch": 0.20236087689713322,
27
- "grad_norm": 0.16402624547481537,
28
- "learning_rate": 9.40297765928369e-05,
29
- "loss": 0.7292,
30
- "step": 30
31
- },
32
- {
33
- "epoch": 0.26981450252951095,
34
- "grad_norm": 0.1697295904159546,
35
- "learning_rate": 8.765357330018056e-05,
36
- "loss": 0.6697,
37
- "step": 40
38
- },
39
- {
40
- "epoch": 0.3372681281618887,
41
- "grad_norm": 0.15344694256782532,
42
- "learning_rate": 7.938926261462366e-05,
43
- "loss": 0.6503,
44
- "step": 50
45
- },
46
- {
47
- "epoch": 0.40472175379426645,
48
- "grad_norm": 0.14287105202674866,
49
- "learning_rate": 6.965125158269619e-05,
50
- "loss": 0.6218,
51
- "step": 60
52
- },
53
- {
54
- "epoch": 0.47217537942664417,
55
- "grad_norm": 0.13973189890384674,
56
- "learning_rate": 5.8927844739931834e-05,
57
- "loss": 0.6289,
58
- "step": 70
59
- },
60
- {
61
- "epoch": 0.5396290050590219,
62
- "grad_norm": 0.1543632447719574,
63
- "learning_rate": 4.775675848247427e-05,
64
- "loss": 0.6173,
65
- "step": 80
66
- },
67
- {
68
- "epoch": 0.6070826306913997,
69
- "grad_norm": 0.14999336004257202,
70
- "learning_rate": 3.6698157721666246e-05,
71
- "loss": 0.632,
72
- "step": 90
73
- },
74
- {
75
- "epoch": 0.6745362563237775,
76
- "grad_norm": 0.15391264855861664,
77
- "learning_rate": 2.630656687635007e-05,
78
- "loss": 0.6116,
79
- "step": 100
80
- },
81
- {
82
- "epoch": 0.7419898819561551,
83
- "grad_norm": 0.17084521055221558,
84
- "learning_rate": 1.7103063703014372e-05,
85
- "loss": 0.6218,
86
- "step": 110
87
- },
88
- {
89
- "epoch": 0.8094435075885329,
90
- "grad_norm": 0.15896837413311005,
91
- "learning_rate": 9.549150281252633e-06,
92
- "loss": 0.5958,
93
- "step": 120
94
- },
95
- {
96
- "epoch": 0.8768971332209107,
97
- "grad_norm": 0.1687677800655365,
98
- "learning_rate": 4.023611372427471e-06,
99
- "loss": 0.6091,
100
- "step": 130
101
- },
102
- {
103
- "epoch": 0.9443507588532883,
104
- "grad_norm": 0.15441162884235382,
105
- "learning_rate": 8.035205700685167e-07,
106
- "loss": 0.6089,
107
- "step": 140
108
- }
109
- ],
110
- "logging_steps": 10,
111
- "max_steps": 148,
112
- "num_input_tokens_seen": 0,
113
- "num_train_epochs": 1,
114
- "save_steps": 500,
115
- "stateful_callbacks": {
116
- "TrainerControl": {
117
- "args": {
118
- "should_epoch_stop": false,
119
- "should_evaluate": false,
120
- "should_log": false,
121
- "should_save": true,
122
- "should_training_stop": true
123
- },
124
- "attributes": {}
125
- }
126
- },
127
- "total_flos": 1.71580067771179e+17,
128
- "train_batch_size": 1,
129
- "trial_name": null,
130
- "trial_params": null
131
- }