vutankiet2901 commited on
Commit
eb7f771
1 Parent(s): dad725b

End of training

Browse files
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "epoch": 2.0,
3
- "eval_cer": 0.9555030929683531,
4
- "eval_loss": 3.2690865993499756,
5
- "eval_runtime": 316.6745,
6
  "eval_samples": 4470,
7
- "eval_samples_per_second": 14.115,
8
- "eval_steps_per_second": 1.765,
9
- "eval_wer": 0.9960036558484615,
10
- "train_loss": 6.151403113256527,
11
- "train_runtime": 1933.761,
12
  "train_samples": 10156,
13
- "train_samples_per_second": 10.504,
14
- "train_steps_per_second": 0.163
15
  }
 
1
  {
2
+ "epoch": 100.0,
3
+ "eval_cer": 0.12175835997967904,
4
+ "eval_loss": 0.33164310455322266,
5
+ "eval_runtime": 269.3321,
6
  "eval_samples": 4470,
7
+ "eval_samples_per_second": 16.597,
8
+ "eval_steps_per_second": 2.076,
9
+ "eval_wer": 0.2563574129495887,
10
+ "train_loss": 1.2220959588545788,
11
+ "train_runtime": 95146.6811,
12
  "train_samples": 10156,
13
+ "train_samples_per_second": 10.674,
14
+ "train_steps_per_second": 0.166
15
  }
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "epoch": 2.0,
3
- "eval_cer": 0.9555030929683531,
4
- "eval_loss": 3.2690865993499756,
5
- "eval_runtime": 316.6745,
6
  "eval_samples": 4470,
7
- "eval_samples_per_second": 14.115,
8
- "eval_steps_per_second": 1.765,
9
- "eval_wer": 0.9960036558484615
10
  }
 
1
  {
2
+ "epoch": 100.0,
3
+ "eval_cer": 0.12175835997967904,
4
+ "eval_loss": 0.33164310455322266,
5
+ "eval_runtime": 269.3321,
6
  "eval_samples": 4470,
7
+ "eval_samples_per_second": 16.597,
8
+ "eval_steps_per_second": 2.076,
9
+ "eval_wer": 0.2563574129495887
10
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07f8723eb955d88bd7404afdfdb91dd19bbc3e2bdf84b4f9891357e18de03047
3
  size 3850912241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3f26f1ec034a6b5009d36284873996f246ddb50af387ad2e3f3ebd16d605b3
3
  size 3850912241
runs/Feb06_00-21-08_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/events.out.tfevents.1644106918.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.39512.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a3b0141c51d24864c14c294ab2bb798af5994e22bc6a77db036cc19b07ae71c
3
- size 7889
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f31d5014dbb9e485d691c1b4bc587365601fe2e371a08612587c526f742942
3
+ size 10331
runs/Feb06_00-21-08_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/events.out.tfevents.1644202339.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.39512.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8e7d6e5d91b945f30cb85b919c8525346be72292882874e125c6a107c76f63
3
+ size 405
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 2.0,
3
- "train_loss": 6.151403113256527,
4
- "train_runtime": 1933.761,
5
  "train_samples": 10156,
6
- "train_samples_per_second": 10.504,
7
- "train_steps_per_second": 0.163
8
  }
 
1
  {
2
+ "epoch": 100.0,
3
+ "train_loss": 1.2220959588545788,
4
+ "train_runtime": 95146.6811,
5
  "train_samples": 10156,
6
+ "train_samples_per_second": 10.674,
7
+ "train_steps_per_second": 0.166
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,185 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.9952755905511812,
5
- "global_step": 316,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 2.0,
12
- "step": 316,
13
- "total_flos": 9.23014088962431e+18,
14
- "train_loss": 6.151403113256527,
15
- "train_runtime": 1933.761,
16
- "train_samples_per_second": 10.504,
17
- "train_steps_per_second": 0.163
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
- "max_steps": 316,
21
- "num_train_epochs": 2,
22
- "total_flos": 9.23014088962431e+18,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
+ "best_metric": 0.33164310455322266,
3
+ "best_model_checkpoint": "wav2vec2-xls-r-1b-ja/checkpoint-15000",
4
+ "epoch": 99.99527559055119,
5
+ "global_step": 15800,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 9.49,
12
+ "learning_rate": 3.7425e-05,
13
+ "loss": 3.484,
14
+ "step": 1500
15
+ },
16
+ {
17
+ "epoch": 9.49,
18
+ "eval_cer": 0.4098974987299405,
19
+ "eval_loss": 1.1849042177200317,
20
+ "eval_runtime": 268.3084,
21
+ "eval_samples_per_second": 16.66,
22
+ "eval_steps_per_second": 2.083,
23
+ "eval_wer": 0.7542696367448612,
24
+ "step": 1500
25
+ },
26
+ {
27
+ "epoch": 18.98,
28
+ "learning_rate": 4.638768115942029e-05,
29
+ "loss": 1.3582,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 18.98,
34
+ "eval_cer": 0.1590532827301796,
35
+ "eval_loss": 0.4320400655269623,
36
+ "eval_runtime": 269.0628,
37
+ "eval_samples_per_second": 16.613,
38
+ "eval_steps_per_second": 2.078,
39
+ "eval_wer": 0.34893639898926543,
40
+ "step": 3000
41
+ },
42
+ {
43
+ "epoch": 28.48,
44
+ "learning_rate": 4.095289855072464e-05,
45
+ "loss": 1.1716,
46
+ "step": 4500
47
+ },
48
+ {
49
+ "epoch": 28.48,
50
+ "eval_cer": 0.1453904312225443,
51
+ "eval_loss": 0.38348379731178284,
52
+ "eval_runtime": 270.1414,
53
+ "eval_samples_per_second": 16.547,
54
+ "eval_steps_per_second": 2.069,
55
+ "eval_wer": 0.31746742889912366,
56
+ "step": 4500
57
+ },
58
+ {
59
+ "epoch": 37.97,
60
+ "learning_rate": 3.552173913043478e-05,
61
+ "loss": 1.0951,
62
+ "step": 6000
63
+ },
64
+ {
65
+ "epoch": 37.97,
66
+ "eval_cer": 0.14047754236021875,
67
+ "eval_loss": 0.3732404410839081,
68
+ "eval_runtime": 272.8075,
69
+ "eval_samples_per_second": 16.385,
70
+ "eval_steps_per_second": 2.049,
71
+ "eval_wer": 0.3032741348721349,
72
+ "step": 6000
73
+ },
74
+ {
75
+ "epoch": 47.47,
76
+ "learning_rate": 3.0090579710144927e-05,
77
+ "loss": 1.04,
78
+ "step": 7500
79
+ },
80
+ {
81
+ "epoch": 47.47,
82
+ "eval_cer": 0.13603681678271523,
83
+ "eval_loss": 0.34847018122673035,
84
+ "eval_runtime": 268.2852,
85
+ "eval_samples_per_second": 16.661,
86
+ "eval_steps_per_second": 2.084,
87
+ "eval_wer": 0.28983351552839554,
88
+ "step": 7500
89
+ },
90
+ {
91
+ "epoch": 56.96,
92
+ "learning_rate": 2.4655797101449275e-05,
93
+ "loss": 0.9768,
94
+ "step": 9000
95
+ },
96
+ {
97
+ "epoch": 56.96,
98
+ "eval_cer": 0.13088485790275828,
99
+ "eval_loss": 0.33858078718185425,
100
+ "eval_runtime": 269.384,
101
+ "eval_samples_per_second": 16.593,
102
+ "eval_steps_per_second": 2.075,
103
+ "eval_wer": 0.278722603537571,
104
+ "step": 9000
105
+ },
106
+ {
107
+ "epoch": 66.45,
108
+ "learning_rate": 1.922463768115942e-05,
109
+ "loss": 0.9129,
110
+ "step": 10500
111
+ },
112
+ {
113
+ "epoch": 66.45,
114
+ "eval_cer": 0.1271553656277082,
115
+ "eval_loss": 0.336273193359375,
116
+ "eval_runtime": 267.776,
117
+ "eval_samples_per_second": 16.693,
118
+ "eval_steps_per_second": 2.088,
119
+ "eval_wer": 0.27108833175032704,
120
+ "step": 10500
121
+ },
122
+ {
123
+ "epoch": 75.94,
124
+ "learning_rate": 1.3793478260869565e-05,
125
+ "loss": 0.8614,
126
+ "step": 12000
127
+ },
128
+ {
129
+ "epoch": 75.94,
130
+ "eval_cer": 0.12596001553955113,
131
+ "eval_loss": 0.33856987953186035,
132
+ "eval_runtime": 268.1172,
133
+ "eval_samples_per_second": 16.672,
134
+ "eval_steps_per_second": 2.085,
135
+ "eval_wer": 0.26755792906937154,
136
+ "step": 12000
137
+ },
138
+ {
139
+ "epoch": 85.44,
140
+ "learning_rate": 8.358695652173914e-06,
141
+ "loss": 0.8092,
142
+ "step": 13500
143
+ },
144
+ {
145
+ "epoch": 85.44,
146
+ "eval_cer": 0.12399964139497355,
147
+ "eval_loss": 0.3356078565120697,
148
+ "eval_runtime": 269.2379,
149
+ "eval_samples_per_second": 16.602,
150
+ "eval_steps_per_second": 2.076,
151
+ "eval_wer": 0.26103474848121,
152
+ "step": 13500
153
+ },
154
+ {
155
+ "epoch": 94.93,
156
+ "learning_rate": 2.9275362318840578e-06,
157
+ "loss": 0.7658,
158
+ "step": 15000
159
+ },
160
+ {
161
+ "epoch": 94.93,
162
+ "eval_cer": 0.12175835997967904,
163
+ "eval_loss": 0.33164310455322266,
164
+ "eval_runtime": 268.5018,
165
+ "eval_samples_per_second": 16.648,
166
+ "eval_steps_per_second": 2.082,
167
+ "eval_wer": 0.2563574129495887,
168
+ "step": 15000
169
+ },
170
+ {
171
+ "epoch": 100.0,
172
+ "step": 15800,
173
+ "total_flos": 4.622164701241047e+20,
174
+ "train_loss": 1.2220959588545788,
175
+ "train_runtime": 95146.6811,
176
+ "train_samples_per_second": 10.674,
177
+ "train_steps_per_second": 0.166
178
  }
179
  ],
180
+ "max_steps": 15800,
181
+ "num_train_epochs": 100,
182
+ "total_flos": 4.622164701241047e+20,
183
  "trial_name": null,
184
  "trial_params": null
185
  }