pplantinga commited on
Commit
2cb5ed0
1 Parent(s): 7afa2eb

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.6,
3
+ "eval_loss": 0.2034856379032135,
4
+ "eval_runtime": 2637.6572,
5
+ "eval_samples_per_second": 4.073,
6
+ "eval_steps_per_second": 0.073,
7
+ "eval_wer": 11.51353061870298,
8
+ "train_loss": 0.24563861989974975,
9
+ "train_runtime": 8940.2743,
10
+ "train_samples_per_second": 6.264,
11
+ "train_steps_per_second": 0.056
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.6,
3
+ "eval_loss": 0.2034856379032135,
4
+ "eval_runtime": 2637.6572,
5
+ "eval_samples_per_second": 4.073,
6
+ "eval_steps_per_second": 0.073,
7
+ "eval_wer": 11.51353061870298
8
+ }
runs/Dec09_22-22-57_ip-172-31-0-249/events.out.tfevents.1670643191.ip-172-31-0-249.85317.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54f7c509e7c7184538bfba85791ec02e810963b148f9fe265d3ec367a4ec7dc
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.6,
3
+ "train_loss": 0.24563861989974975,
4
+ "train_runtime": 8940.2743,
5
+ "train_samples_per_second": 6.264,
6
+ "train_steps_per_second": 0.056
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6041666666666665,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.13,
12
+ "learning_rate": 5.000000000000001e-07,
13
+ "loss": 1.062,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.26,
18
+ "learning_rate": 1.0000000000000002e-06,
19
+ "loss": 0.854,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.39,
24
+ "learning_rate": 1.5e-06,
25
+ "loss": 0.4782,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.52,
30
+ "learning_rate": 2.0000000000000003e-06,
31
+ "loss": 0.2736,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.65,
36
+ "learning_rate": 2.5e-06,
37
+ "loss": 0.2359,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.78,
42
+ "learning_rate": 3e-06,
43
+ "loss": 0.2051,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.91,
48
+ "learning_rate": 3.5e-06,
49
+ "loss": 0.2034,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 1.04,
54
+ "learning_rate": 4.000000000000001e-06,
55
+ "loss": 0.1865,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 1.17,
60
+ "learning_rate": 4.5e-06,
61
+ "loss": 0.1539,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 1.3,
66
+ "learning_rate": 5e-06,
67
+ "loss": 0.1522,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 1.43,
72
+ "learning_rate": 5.500000000000001e-06,
73
+ "loss": 0.1443,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 1.56,
78
+ "learning_rate": 6e-06,
79
+ "loss": 0.1408,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 1.69,
84
+ "learning_rate": 6.5000000000000004e-06,
85
+ "loss": 0.1356,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 1.82,
90
+ "learning_rate": 7e-06,
91
+ "loss": 0.1346,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 1.95,
96
+ "learning_rate": 7.500000000000001e-06,
97
+ "loss": 0.1333,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 2.08,
102
+ "learning_rate": 8.000000000000001e-06,
103
+ "loss": 0.0989,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 2.21,
108
+ "learning_rate": 8.5e-06,
109
+ "loss": 0.0798,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 2.34,
114
+ "learning_rate": 9e-06,
115
+ "loss": 0.0823,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 2.47,
120
+ "learning_rate": 9.5e-06,
121
+ "loss": 0.0766,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 2.6,
126
+ "learning_rate": 0.0,
127
+ "loss": 0.0818,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 2.6,
132
+ "step": 500,
133
+ "total_flos": 1.614231295229952e+19,
134
+ "train_loss": 0.24563861989974975,
135
+ "train_runtime": 8940.2743,
136
+ "train_samples_per_second": 6.264,
137
+ "train_steps_per_second": 0.056
138
+ }
139
+ ],
140
+ "max_steps": 500,
141
+ "num_train_epochs": 3,
142
+ "total_flos": 1.614231295229952e+19,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }