qmeeus commited on
Commit
e7bd3de
1 Parent(s): 3ec01da

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.19,
3
+ "eval_loss": 0.38643914461135864,
4
+ "eval_runtime": 204.4048,
5
+ "eval_samples": 1000,
6
+ "eval_samples_per_second": 4.892,
7
+ "eval_steps_per_second": 0.078,
8
+ "eval_wer": 18.367063400175983,
9
+ "train_loss": 0.4157425765991211,
10
+ "train_runtime": 7330.7001,
11
+ "train_samples_per_second": 69.843,
12
+ "train_steps_per_second": 0.136
13
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.19,
3
+ "eval_loss": 0.38643914461135864,
4
+ "eval_runtime": 204.4048,
5
+ "eval_samples": 1000,
6
+ "eval_samples_per_second": 4.892,
7
+ "eval_steps_per_second": 0.078,
8
+ "eval_wer": 18.367063400175983
9
+ }
runs/Dec14_02-23-18_168-138-34-114/events.out.tfevents.1670992423.168-138-34-114.259544.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273c999b7443cad814b3255d091356cb41abb715dc4cf3745c6e4ef4126358e5
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.19,
3
+ "train_loss": 0.4157425765991211,
4
+ "train_runtime": 7330.7001,
5
+ "train_samples_per_second": 69.843,
6
+ "train_steps_per_second": 0.136
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 18.367063400175983,
3
+ "best_model_checkpoint": "./whisper-small-nl/checkpoint-600",
4
+ "epoch": 1.194,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 9.473684210526315e-06,
13
+ "loss": 0.8378,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_loss": 0.4932844042778015,
19
+ "eval_runtime": 153.0661,
20
+ "eval_samples_per_second": 6.533,
21
+ "eval_steps_per_second": 0.105,
22
+ "eval_wer": 23.882739776779513,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.2,
27
+ "learning_rate": 8.421052631578948e-06,
28
+ "loss": 0.5547,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.2,
33
+ "eval_loss": 0.44761189818382263,
34
+ "eval_runtime": 154.0782,
35
+ "eval_samples_per_second": 6.49,
36
+ "eval_steps_per_second": 0.104,
37
+ "eval_wer": 21.057750196823044,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.3,
42
+ "learning_rate": 7.368421052631579e-06,
43
+ "loss": 0.3905,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.3,
48
+ "eval_loss": 0.4335392117500305,
49
+ "eval_runtime": 152.7461,
50
+ "eval_samples_per_second": 6.547,
51
+ "eval_steps_per_second": 0.105,
52
+ "eval_wer": 21.168897327837723,
53
+ "step": 300
54
+ },
55
+ {
56
+ "epoch": 0.4,
57
+ "learning_rate": 6.31578947368421e-06,
58
+ "loss": 0.3766,
59
+ "step": 400
60
+ },
61
+ {
62
+ "epoch": 0.4,
63
+ "eval_loss": 0.4266929030418396,
64
+ "eval_runtime": 150.336,
65
+ "eval_samples_per_second": 6.652,
66
+ "eval_steps_per_second": 0.106,
67
+ "eval_wer": 20.052794887231972,
68
+ "step": 400
69
+ },
70
+ {
71
+ "epoch": 0.5,
72
+ "learning_rate": 5.263157894736842e-06,
73
+ "loss": 0.4164,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.5,
78
+ "eval_loss": 0.4138640761375427,
79
+ "eval_runtime": 157.7477,
80
+ "eval_samples_per_second": 6.339,
81
+ "eval_steps_per_second": 0.101,
82
+ "eval_wer": 21.43287176399759,
83
+ "step": 500
84
+ },
85
+ {
86
+ "epoch": 0.6,
87
+ "learning_rate": 4.210526315789474e-06,
88
+ "loss": 0.2939,
89
+ "step": 600
90
+ },
91
+ {
92
+ "epoch": 0.6,
93
+ "eval_loss": 0.38643914461135864,
94
+ "eval_runtime": 151.6414,
95
+ "eval_samples_per_second": 6.595,
96
+ "eval_steps_per_second": 0.106,
97
+ "eval_wer": 18.367063400175983,
98
+ "step": 600
99
+ },
100
+ {
101
+ "epoch": 0.7,
102
+ "learning_rate": 3.157894736842105e-06,
103
+ "loss": 0.2632,
104
+ "step": 700
105
+ },
106
+ {
107
+ "epoch": 0.7,
108
+ "eval_loss": 0.3864086866378784,
109
+ "eval_runtime": 152.5897,
110
+ "eval_samples_per_second": 6.554,
111
+ "eval_steps_per_second": 0.105,
112
+ "eval_wer": 18.431899226601214,
113
+ "step": 700
114
+ },
115
+ {
116
+ "epoch": 0.8,
117
+ "learning_rate": 2.105263157894737e-06,
118
+ "loss": 0.6066,
119
+ "step": 800
120
+ },
121
+ {
122
+ "epoch": 0.8,
123
+ "eval_loss": 0.3804214298725128,
124
+ "eval_runtime": 156.1258,
125
+ "eval_samples_per_second": 6.405,
126
+ "eval_steps_per_second": 0.102,
127
+ "eval_wer": 19.27476497012921,
128
+ "step": 800
129
+ },
130
+ {
131
+ "epoch": 1.09,
132
+ "learning_rate": 1.0526315789473685e-06,
133
+ "loss": 0.2075,
134
+ "step": 900
135
+ },
136
+ {
137
+ "epoch": 1.09,
138
+ "eval_loss": 0.3793680667877197,
139
+ "eval_runtime": 153.2522,
140
+ "eval_samples_per_second": 6.525,
141
+ "eval_steps_per_second": 0.104,
142
+ "eval_wer": 18.890381142036773,
143
+ "step": 900
144
+ },
145
+ {
146
+ "epoch": 1.19,
147
+ "learning_rate": 0.0,
148
+ "loss": 0.2102,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 1.19,
153
+ "eval_loss": 0.37768101692199707,
154
+ "eval_runtime": 153.5387,
155
+ "eval_samples_per_second": 6.513,
156
+ "eval_steps_per_second": 0.104,
157
+ "eval_wer": 19.88144306025101,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 1.19,
162
+ "step": 1000,
163
+ "total_flos": 1.84579222044672e+19,
164
+ "train_loss": 0.4157425765991211,
165
+ "train_runtime": 7330.7001,
166
+ "train_samples_per_second": 69.843,
167
+ "train_steps_per_second": 0.136
168
+ }
169
+ ],
170
+ "max_steps": 1000,
171
+ "num_train_epochs": 9223372036854775807,
172
+ "total_flos": 1.84579222044672e+19,
173
+ "trial_name": null,
174
+ "trial_params": null
175
+ }