Yasinjan99
commited on
Commit
•
8af493d
1
Parent(s):
8f60edc
End of training
Browse files- README.md +8 -17
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +910 -0
README.md
CHANGED
@@ -1,7 +1,11 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_11_0
|
@@ -9,20 +13,7 @@ metrics:
|
|
9 |
- wer
|
10 |
model-index:
|
11 |
- name: xls-r-uyghur-cv11
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
name: Automatic Speech Recognition
|
15 |
-
type: automatic-speech-recognition
|
16 |
-
dataset:
|
17 |
-
name: common_voice_11_0
|
18 |
-
type: common_voice_11_0
|
19 |
-
config: ug
|
20 |
-
split: test
|
21 |
-
args: ug
|
22 |
-
metrics:
|
23 |
-
- name: Wer
|
24 |
-
type: wer
|
25 |
-
value: 0.32705699280295664
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# xls-r-uyghur-cv11
|
32 |
|
33 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Wer: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- ug
|
4 |
license: apache-2.0
|
5 |
base_model: facebook/wav2vec2-xls-r-300m
|
6 |
tags:
|
7 |
+
- automatic-speech-recognition
|
8 |
+
- mozilla-foundation/common_voice_11_0
|
9 |
- generated_from_trainer
|
10 |
datasets:
|
11 |
- common_voice_11_0
|
|
|
13 |
- wer
|
14 |
model-index:
|
15 |
- name: xls-r-uyghur-cv11
|
16 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
---
|
18 |
|
19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
21 |
|
22 |
# xls-r-uyghur-cv11
|
23 |
|
24 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_11_0 - UG dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
+
- Loss: 0.2191
|
27 |
+
- Wer: 0.3257
|
28 |
|
29 |
## Model description
|
30 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 99.35,
|
3 |
+
"eval_loss": 0.21905453503131866,
|
4 |
+
"eval_runtime": 260.5584,
|
5 |
+
"eval_samples": 3270,
|
6 |
+
"eval_samples_per_second": 12.55,
|
7 |
+
"eval_steps_per_second": 1.57,
|
8 |
+
"eval_wer": 0.32569539000194514,
|
9 |
+
"train_loss": 1.3810767638892458,
|
10 |
+
"train_runtime": 73797.3063,
|
11 |
+
"train_samples": 7342,
|
12 |
+
"train_samples_per_second": 9.949,
|
13 |
+
"train_steps_per_second": 0.154
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 99.35,
|
3 |
+
"eval_loss": 0.21905453503131866,
|
4 |
+
"eval_runtime": 260.5584,
|
5 |
+
"eval_samples": 3270,
|
6 |
+
"eval_samples_per_second": 12.55,
|
7 |
+
"eval_steps_per_second": 1.57,
|
8 |
+
"eval_wer": 0.32569539000194514
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 99.35,
|
3 |
+
"train_loss": 1.3810767638892458,
|
4 |
+
"train_runtime": 73797.3063,
|
5 |
+
"train_samples": 7342,
|
6 |
+
"train_samples_per_second": 9.949,
|
7 |
+
"train_steps_per_second": 0.154
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,910 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 99.34640522875817,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 11400,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.87,
|
13 |
+
"learning_rate": 4.950000000000001e-06,
|
14 |
+
"loss": 14.1952,
|
15 |
+
"step": 100
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.74,
|
19 |
+
"learning_rate": 9.950000000000001e-06,
|
20 |
+
"loss": 6.4908,
|
21 |
+
"step": 200
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 2.61,
|
25 |
+
"learning_rate": 1.4950000000000001e-05,
|
26 |
+
"loss": 4.5428,
|
27 |
+
"step": 300
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.49,
|
31 |
+
"learning_rate": 1.995e-05,
|
32 |
+
"loss": 3.8598,
|
33 |
+
"step": 400
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 4.36,
|
37 |
+
"learning_rate": 2.495e-05,
|
38 |
+
"loss": 3.3958,
|
39 |
+
"step": 500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.36,
|
43 |
+
"eval_loss": 3.3137385845184326,
|
44 |
+
"eval_runtime": 268.8924,
|
45 |
+
"eval_samples_per_second": 12.161,
|
46 |
+
"eval_steps_per_second": 1.521,
|
47 |
+
"eval_wer": 1.0,
|
48 |
+
"step": 500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 5.23,
|
52 |
+
"learning_rate": 2.995e-05,
|
53 |
+
"loss": 3.2375,
|
54 |
+
"step": 600
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 6.1,
|
58 |
+
"learning_rate": 3.495e-05,
|
59 |
+
"loss": 3.1969,
|
60 |
+
"step": 700
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 6.97,
|
64 |
+
"learning_rate": 3.995e-05,
|
65 |
+
"loss": 3.151,
|
66 |
+
"step": 800
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 7.84,
|
70 |
+
"learning_rate": 4.495e-05,
|
71 |
+
"loss": 3.1114,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 8.71,
|
76 |
+
"learning_rate": 4.995e-05,
|
77 |
+
"loss": 3.032,
|
78 |
+
"step": 1000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 8.71,
|
82 |
+
"eval_loss": 2.858614921569824,
|
83 |
+
"eval_runtime": 245.2843,
|
84 |
+
"eval_samples_per_second": 13.331,
|
85 |
+
"eval_steps_per_second": 1.667,
|
86 |
+
"eval_wer": 0.9992608441937366,
|
87 |
+
"step": 1000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 9.59,
|
91 |
+
"learning_rate": 5.495e-05,
|
92 |
+
"loss": 2.5279,
|
93 |
+
"step": 1100
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 10.46,
|
97 |
+
"learning_rate": 5.995000000000001e-05,
|
98 |
+
"loss": 1.8013,
|
99 |
+
"step": 1200
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 11.33,
|
103 |
+
"learning_rate": 6.494999999999999e-05,
|
104 |
+
"loss": 1.5785,
|
105 |
+
"step": 1300
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 12.2,
|
109 |
+
"learning_rate": 6.995e-05,
|
110 |
+
"loss": 1.468,
|
111 |
+
"step": 1400
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 13.07,
|
115 |
+
"learning_rate": 7.495e-05,
|
116 |
+
"loss": 1.3977,
|
117 |
+
"step": 1500
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 13.07,
|
121 |
+
"eval_loss": 0.4785650372505188,
|
122 |
+
"eval_runtime": 252.0133,
|
123 |
+
"eval_samples_per_second": 12.976,
|
124 |
+
"eval_steps_per_second": 1.623,
|
125 |
+
"eval_wer": 0.637541334370745,
|
126 |
+
"step": 1500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 13.94,
|
130 |
+
"learning_rate": 7.99e-05,
|
131 |
+
"loss": 1.3681,
|
132 |
+
"step": 1600
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 14.81,
|
136 |
+
"learning_rate": 8.49e-05,
|
137 |
+
"loss": 1.336,
|
138 |
+
"step": 1700
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 15.69,
|
142 |
+
"learning_rate": 8.99e-05,
|
143 |
+
"loss": 1.307,
|
144 |
+
"step": 1800
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 16.56,
|
148 |
+
"learning_rate": 9.49e-05,
|
149 |
+
"loss": 1.2934,
|
150 |
+
"step": 1900
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 17.43,
|
154 |
+
"learning_rate": 9.99e-05,
|
155 |
+
"loss": 1.2751,
|
156 |
+
"step": 2000
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 17.43,
|
160 |
+
"eval_loss": 0.3816487491130829,
|
161 |
+
"eval_runtime": 244.8161,
|
162 |
+
"eval_samples_per_second": 13.357,
|
163 |
+
"eval_steps_per_second": 1.671,
|
164 |
+
"eval_wer": 0.53931141801206,
|
165 |
+
"step": 2000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 18.3,
|
169 |
+
"learning_rate": 9.895744680851065e-05,
|
170 |
+
"loss": 1.2545,
|
171 |
+
"step": 2100
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 19.17,
|
175 |
+
"learning_rate": 9.78936170212766e-05,
|
176 |
+
"loss": 1.2488,
|
177 |
+
"step": 2200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 20.04,
|
181 |
+
"learning_rate": 9.682978723404255e-05,
|
182 |
+
"loss": 1.2315,
|
183 |
+
"step": 2300
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 20.92,
|
187 |
+
"learning_rate": 9.576595744680852e-05,
|
188 |
+
"loss": 1.2237,
|
189 |
+
"step": 2400
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 21.79,
|
193 |
+
"learning_rate": 9.470212765957447e-05,
|
194 |
+
"loss": 1.2113,
|
195 |
+
"step": 2500
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 21.79,
|
199 |
+
"eval_loss": 0.3450602889060974,
|
200 |
+
"eval_runtime": 260.0099,
|
201 |
+
"eval_samples_per_second": 12.576,
|
202 |
+
"eval_steps_per_second": 1.573,
|
203 |
+
"eval_wer": 0.509900797510212,
|
204 |
+
"step": 2500
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 22.66,
|
208 |
+
"learning_rate": 9.363829787234043e-05,
|
209 |
+
"loss": 1.204,
|
210 |
+
"step": 2600
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 23.53,
|
214 |
+
"learning_rate": 9.257446808510639e-05,
|
215 |
+
"loss": 1.1834,
|
216 |
+
"step": 2700
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 24.4,
|
220 |
+
"learning_rate": 9.151063829787234e-05,
|
221 |
+
"loss": 1.1782,
|
222 |
+
"step": 2800
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 25.27,
|
226 |
+
"learning_rate": 9.04468085106383e-05,
|
227 |
+
"loss": 1.1616,
|
228 |
+
"step": 2900
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 26.14,
|
232 |
+
"learning_rate": 8.938297872340426e-05,
|
233 |
+
"loss": 1.156,
|
234 |
+
"step": 3000
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 26.14,
|
238 |
+
"eval_loss": 0.3244517743587494,
|
239 |
+
"eval_runtime": 254.1562,
|
240 |
+
"eval_samples_per_second": 12.866,
|
241 |
+
"eval_steps_per_second": 1.609,
|
242 |
+
"eval_wer": 0.49192764053686056,
|
243 |
+
"step": 3000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 27.02,
|
247 |
+
"learning_rate": 8.831914893617022e-05,
|
248 |
+
"loss": 1.165,
|
249 |
+
"step": 3100
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 27.89,
|
253 |
+
"learning_rate": 8.725531914893618e-05,
|
254 |
+
"loss": 1.1559,
|
255 |
+
"step": 3200
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 28.76,
|
259 |
+
"learning_rate": 8.619148936170212e-05,
|
260 |
+
"loss": 1.1239,
|
261 |
+
"step": 3300
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 29.63,
|
265 |
+
"learning_rate": 8.51276595744681e-05,
|
266 |
+
"loss": 1.1219,
|
267 |
+
"step": 3400
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 30.5,
|
271 |
+
"learning_rate": 8.406382978723405e-05,
|
272 |
+
"loss": 1.1226,
|
273 |
+
"step": 3500
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 30.5,
|
277 |
+
"eval_loss": 0.2992089092731476,
|
278 |
+
"eval_runtime": 263.7476,
|
279 |
+
"eval_samples_per_second": 12.398,
|
280 |
+
"eval_steps_per_second": 1.551,
|
281 |
+
"eval_wer": 0.44411593075277184,
|
282 |
+
"step": 3500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 31.37,
|
286 |
+
"learning_rate": 8.3e-05,
|
287 |
+
"loss": 1.1115,
|
288 |
+
"step": 3600
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 32.24,
|
292 |
+
"learning_rate": 8.194680851063831e-05,
|
293 |
+
"loss": 1.0983,
|
294 |
+
"step": 3700
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 33.12,
|
298 |
+
"learning_rate": 8.088297872340426e-05,
|
299 |
+
"loss": 1.0957,
|
300 |
+
"step": 3800
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 33.99,
|
304 |
+
"learning_rate": 7.981914893617022e-05,
|
305 |
+
"loss": 1.0874,
|
306 |
+
"step": 3900
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 34.86,
|
310 |
+
"learning_rate": 7.875531914893617e-05,
|
311 |
+
"loss": 1.0913,
|
312 |
+
"step": 4000
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 34.86,
|
316 |
+
"eval_loss": 0.2831476330757141,
|
317 |
+
"eval_runtime": 264.6688,
|
318 |
+
"eval_samples_per_second": 12.355,
|
319 |
+
"eval_steps_per_second": 1.545,
|
320 |
+
"eval_wer": 0.431472476171951,
|
321 |
+
"step": 4000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 35.73,
|
325 |
+
"learning_rate": 7.769148936170213e-05,
|
326 |
+
"loss": 1.0896,
|
327 |
+
"step": 4100
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 36.6,
|
331 |
+
"learning_rate": 7.663829787234042e-05,
|
332 |
+
"loss": 1.071,
|
333 |
+
"step": 4200
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 37.47,
|
337 |
+
"learning_rate": 7.557446808510639e-05,
|
338 |
+
"loss": 1.0635,
|
339 |
+
"step": 4300
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 38.34,
|
343 |
+
"learning_rate": 7.451063829787235e-05,
|
344 |
+
"loss": 1.0689,
|
345 |
+
"step": 4400
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 39.22,
|
349 |
+
"learning_rate": 7.34468085106383e-05,
|
350 |
+
"loss": 1.0615,
|
351 |
+
"step": 4500
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 39.22,
|
355 |
+
"eval_loss": 0.2807982563972473,
|
356 |
+
"eval_runtime": 253.9269,
|
357 |
+
"eval_samples_per_second": 12.878,
|
358 |
+
"eval_steps_per_second": 1.611,
|
359 |
+
"eval_wer": 0.4339622641509434,
|
360 |
+
"step": 4500
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 40.09,
|
364 |
+
"learning_rate": 7.238297872340425e-05,
|
365 |
+
"loss": 1.0553,
|
366 |
+
"step": 4600
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 40.96,
|
370 |
+
"learning_rate": 7.131914893617023e-05,
|
371 |
+
"loss": 1.0533,
|
372 |
+
"step": 4700
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 41.83,
|
376 |
+
"learning_rate": 7.025531914893617e-05,
|
377 |
+
"loss": 1.0546,
|
378 |
+
"step": 4800
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 42.7,
|
382 |
+
"learning_rate": 6.919148936170213e-05,
|
383 |
+
"loss": 1.0517,
|
384 |
+
"step": 4900
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 43.57,
|
388 |
+
"learning_rate": 6.812765957446809e-05,
|
389 |
+
"loss": 1.0455,
|
390 |
+
"step": 5000
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 43.57,
|
394 |
+
"eval_loss": 0.27128756046295166,
|
395 |
+
"eval_runtime": 251.6872,
|
396 |
+
"eval_samples_per_second": 12.992,
|
397 |
+
"eval_steps_per_second": 1.625,
|
398 |
+
"eval_wer": 0.4087531608636452,
|
399 |
+
"step": 5000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 44.44,
|
403 |
+
"learning_rate": 6.706382978723405e-05,
|
404 |
+
"loss": 1.0386,
|
405 |
+
"step": 5100
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 45.32,
|
409 |
+
"learning_rate": 6.6e-05,
|
410 |
+
"loss": 1.0287,
|
411 |
+
"step": 5200
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 46.19,
|
415 |
+
"learning_rate": 6.493617021276595e-05,
|
416 |
+
"loss": 1.0251,
|
417 |
+
"step": 5300
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 47.06,
|
421 |
+
"learning_rate": 6.387234042553192e-05,
|
422 |
+
"loss": 1.0335,
|
423 |
+
"step": 5400
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 47.93,
|
427 |
+
"learning_rate": 6.280851063829788e-05,
|
428 |
+
"loss": 1.0228,
|
429 |
+
"step": 5500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 47.93,
|
433 |
+
"eval_loss": 0.2622440457344055,
|
434 |
+
"eval_runtime": 249.5189,
|
435 |
+
"eval_samples_per_second": 13.105,
|
436 |
+
"eval_steps_per_second": 1.639,
|
437 |
+
"eval_wer": 0.39599299747130906,
|
438 |
+
"step": 5500
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 48.8,
|
442 |
+
"learning_rate": 6.174468085106383e-05,
|
443 |
+
"loss": 1.0184,
|
444 |
+
"step": 5600
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 49.67,
|
448 |
+
"learning_rate": 6.068085106382979e-05,
|
449 |
+
"loss": 1.0174,
|
450 |
+
"step": 5700
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 50.54,
|
454 |
+
"learning_rate": 5.9617021276595755e-05,
|
455 |
+
"loss": 1.0133,
|
456 |
+
"step": 5800
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 51.42,
|
460 |
+
"learning_rate": 5.85531914893617e-05,
|
461 |
+
"loss": 1.0108,
|
462 |
+
"step": 5900
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 52.29,
|
466 |
+
"learning_rate": 5.7489361702127666e-05,
|
467 |
+
"loss": 0.9936,
|
468 |
+
"step": 6000
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 52.29,
|
472 |
+
"eval_loss": 0.25247836112976074,
|
473 |
+
"eval_runtime": 249.2066,
|
474 |
+
"eval_samples_per_second": 13.122,
|
475 |
+
"eval_steps_per_second": 1.641,
|
476 |
+
"eval_wer": 0.37957595798482785,
|
477 |
+
"step": 6000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 53.16,
|
481 |
+
"learning_rate": 5.642553191489362e-05,
|
482 |
+
"loss": 1.0015,
|
483 |
+
"step": 6100
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 54.03,
|
487 |
+
"learning_rate": 5.5361702127659576e-05,
|
488 |
+
"loss": 1.0003,
|
489 |
+
"step": 6200
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 54.9,
|
493 |
+
"learning_rate": 5.429787234042554e-05,
|
494 |
+
"loss": 0.988,
|
495 |
+
"step": 6300
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 55.77,
|
499 |
+
"learning_rate": 5.3234042553191486e-05,
|
500 |
+
"loss": 0.9845,
|
501 |
+
"step": 6400
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 56.64,
|
505 |
+
"learning_rate": 5.217021276595745e-05,
|
506 |
+
"loss": 0.968,
|
507 |
+
"step": 6500
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 56.64,
|
511 |
+
"eval_loss": 0.2505591809749603,
|
512 |
+
"eval_runtime": 253.8437,
|
513 |
+
"eval_samples_per_second": 12.882,
|
514 |
+
"eval_steps_per_second": 1.611,
|
515 |
+
"eval_wer": 0.3798093756078584,
|
516 |
+
"step": 6500
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 57.52,
|
520 |
+
"learning_rate": 5.110638297872341e-05,
|
521 |
+
"loss": 0.9852,
|
522 |
+
"step": 6600
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 58.39,
|
526 |
+
"learning_rate": 5.004255319148936e-05,
|
527 |
+
"loss": 0.9737,
|
528 |
+
"step": 6700
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 59.26,
|
532 |
+
"learning_rate": 4.897872340425532e-05,
|
533 |
+
"loss": 0.9752,
|
534 |
+
"step": 6800
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 60.13,
|
538 |
+
"learning_rate": 4.792553191489362e-05,
|
539 |
+
"loss": 0.9717,
|
540 |
+
"step": 6900
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 61.0,
|
544 |
+
"learning_rate": 4.686170212765958e-05,
|
545 |
+
"loss": 0.9704,
|
546 |
+
"step": 7000
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 61.0,
|
550 |
+
"eval_loss": 0.24809595942497253,
|
551 |
+
"eval_runtime": 257.0988,
|
552 |
+
"eval_samples_per_second": 12.719,
|
553 |
+
"eval_steps_per_second": 1.591,
|
554 |
+
"eval_wer": 0.37346819684886207,
|
555 |
+
"step": 7000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 61.87,
|
559 |
+
"learning_rate": 4.579787234042554e-05,
|
560 |
+
"loss": 0.9603,
|
561 |
+
"step": 7100
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 62.75,
|
565 |
+
"learning_rate": 4.474468085106383e-05,
|
566 |
+
"loss": 0.967,
|
567 |
+
"step": 7200
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 63.62,
|
571 |
+
"learning_rate": 4.368085106382979e-05,
|
572 |
+
"loss": 0.9623,
|
573 |
+
"step": 7300
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 64.49,
|
577 |
+
"learning_rate": 4.261702127659575e-05,
|
578 |
+
"loss": 0.9506,
|
579 |
+
"step": 7400
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 65.36,
|
583 |
+
"learning_rate": 4.15531914893617e-05,
|
584 |
+
"loss": 0.9552,
|
585 |
+
"step": 7500
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 65.36,
|
589 |
+
"eval_loss": 0.23935528099536896,
|
590 |
+
"eval_runtime": 264.2571,
|
591 |
+
"eval_samples_per_second": 12.374,
|
592 |
+
"eval_steps_per_second": 1.548,
|
593 |
+
"eval_wer": 0.36432600661349934,
|
594 |
+
"step": 7500
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 66.23,
|
598 |
+
"learning_rate": 4.048936170212766e-05,
|
599 |
+
"loss": 0.9449,
|
600 |
+
"step": 7600
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 67.1,
|
604 |
+
"learning_rate": 3.9425531914893624e-05,
|
605 |
+
"loss": 0.9411,
|
606 |
+
"step": 7700
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 67.97,
|
610 |
+
"learning_rate": 3.8361702127659576e-05,
|
611 |
+
"loss": 0.9468,
|
612 |
+
"step": 7800
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 68.85,
|
616 |
+
"learning_rate": 3.7297872340425534e-05,
|
617 |
+
"loss": 0.9448,
|
618 |
+
"step": 7900
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 69.72,
|
622 |
+
"learning_rate": 3.6234042553191486e-05,
|
623 |
+
"loss": 0.9417,
|
624 |
+
"step": 8000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 69.72,
|
628 |
+
"eval_loss": 0.23499037325382233,
|
629 |
+
"eval_runtime": 254.8702,
|
630 |
+
"eval_samples_per_second": 12.83,
|
631 |
+
"eval_steps_per_second": 1.605,
|
632 |
+
"eval_wer": 0.35366660182843807,
|
633 |
+
"step": 8000
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 70.59,
|
637 |
+
"learning_rate": 3.517021276595745e-05,
|
638 |
+
"loss": 0.9342,
|
639 |
+
"step": 8100
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 71.46,
|
643 |
+
"learning_rate": 3.41063829787234e-05,
|
644 |
+
"loss": 0.9338,
|
645 |
+
"step": 8200
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 72.33,
|
649 |
+
"learning_rate": 3.304255319148936e-05,
|
650 |
+
"loss": 0.9298,
|
651 |
+
"step": 8300
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 73.2,
|
655 |
+
"learning_rate": 3.1978723404255326e-05,
|
656 |
+
"loss": 0.9239,
|
657 |
+
"step": 8400
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 74.07,
|
661 |
+
"learning_rate": 3.091489361702128e-05,
|
662 |
+
"loss": 0.9215,
|
663 |
+
"step": 8500
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 74.07,
|
667 |
+
"eval_loss": 0.23256558179855347,
|
668 |
+
"eval_runtime": 242.8597,
|
669 |
+
"eval_samples_per_second": 13.465,
|
670 |
+
"eval_steps_per_second": 1.684,
|
671 |
+
"eval_wer": 0.35070997860338454,
|
672 |
+
"step": 8500
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 74.95,
|
676 |
+
"learning_rate": 2.9851063829787236e-05,
|
677 |
+
"loss": 0.9233,
|
678 |
+
"step": 8600
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 75.82,
|
682 |
+
"learning_rate": 2.878723404255319e-05,
|
683 |
+
"loss": 0.9193,
|
684 |
+
"step": 8700
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 76.69,
|
688 |
+
"learning_rate": 2.7723404255319153e-05,
|
689 |
+
"loss": 0.9186,
|
690 |
+
"step": 8800
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 77.56,
|
694 |
+
"learning_rate": 2.6659574468085108e-05,
|
695 |
+
"loss": 0.9064,
|
696 |
+
"step": 8900
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 78.43,
|
700 |
+
"learning_rate": 2.5595744680851063e-05,
|
701 |
+
"loss": 0.9097,
|
702 |
+
"step": 9000
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 78.43,
|
706 |
+
"eval_loss": 0.227674201130867,
|
707 |
+
"eval_runtime": 258.8243,
|
708 |
+
"eval_samples_per_second": 12.634,
|
709 |
+
"eval_steps_per_second": 1.58,
|
710 |
+
"eval_wer": 0.348725928807625,
|
711 |
+
"step": 9000
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 79.3,
|
715 |
+
"learning_rate": 2.453191489361702e-05,
|
716 |
+
"loss": 0.9029,
|
717 |
+
"step": 9100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 80.17,
|
721 |
+
"learning_rate": 2.346808510638298e-05,
|
722 |
+
"loss": 0.9137,
|
723 |
+
"step": 9200
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 81.05,
|
727 |
+
"learning_rate": 2.2404255319148938e-05,
|
728 |
+
"loss": 0.9045,
|
729 |
+
"step": 9300
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 81.92,
|
733 |
+
"learning_rate": 2.1340425531914897e-05,
|
734 |
+
"loss": 0.905,
|
735 |
+
"step": 9400
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 82.79,
|
739 |
+
"learning_rate": 2.027659574468085e-05,
|
740 |
+
"loss": 0.9003,
|
741 |
+
"step": 9500
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 82.79,
|
745 |
+
"eval_loss": 0.2229508012533188,
|
746 |
+
"eval_runtime": 256.366,
|
747 |
+
"eval_samples_per_second": 12.755,
|
748 |
+
"eval_steps_per_second": 1.595,
|
749 |
+
"eval_wer": 0.33623808597549115,
|
750 |
+
"step": 9500
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 83.66,
|
754 |
+
"learning_rate": 1.921276595744681e-05,
|
755 |
+
"loss": 0.8983,
|
756 |
+
"step": 9600
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 84.53,
|
760 |
+
"learning_rate": 1.8148936170212765e-05,
|
761 |
+
"loss": 0.9026,
|
762 |
+
"step": 9700
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 85.4,
|
766 |
+
"learning_rate": 1.7095744680851063e-05,
|
767 |
+
"loss": 0.8921,
|
768 |
+
"step": 9800
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 86.27,
|
772 |
+
"learning_rate": 1.603191489361702e-05,
|
773 |
+
"loss": 0.895,
|
774 |
+
"step": 9900
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 87.15,
|
778 |
+
"learning_rate": 1.4968085106382978e-05,
|
779 |
+
"loss": 0.8857,
|
780 |
+
"step": 10000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 87.15,
|
784 |
+
"eval_loss": 0.2246018499135971,
|
785 |
+
"eval_runtime": 255.6354,
|
786 |
+
"eval_samples_per_second": 12.792,
|
787 |
+
"eval_steps_per_second": 1.6,
|
788 |
+
"eval_wer": 0.3361602801011476,
|
789 |
+
"step": 10000
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 88.02,
|
793 |
+
"learning_rate": 1.3904255319148937e-05,
|
794 |
+
"loss": 0.8916,
|
795 |
+
"step": 10100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 88.89,
|
799 |
+
"learning_rate": 1.2840425531914893e-05,
|
800 |
+
"loss": 0.8808,
|
801 |
+
"step": 10200
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 89.76,
|
805 |
+
"learning_rate": 1.1776595744680852e-05,
|
806 |
+
"loss": 0.8817,
|
807 |
+
"step": 10300
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 90.63,
|
811 |
+
"learning_rate": 1.0712765957446808e-05,
|
812 |
+
"loss": 0.8805,
|
813 |
+
"step": 10400
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 91.5,
|
817 |
+
"learning_rate": 9.648936170212767e-06,
|
818 |
+
"loss": 0.882,
|
819 |
+
"step": 10500
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 91.5,
|
823 |
+
"eval_loss": 0.2236073762178421,
|
824 |
+
"eval_runtime": 260.0762,
|
825 |
+
"eval_samples_per_second": 12.573,
|
826 |
+
"eval_steps_per_second": 1.573,
|
827 |
+
"eval_wer": 0.3315308305777086,
|
828 |
+
"step": 10500
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 92.37,
|
832 |
+
"learning_rate": 8.585106382978724e-06,
|
833 |
+
"loss": 0.8768,
|
834 |
+
"step": 10600
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 93.25,
|
838 |
+
"learning_rate": 7.521276595744681e-06,
|
839 |
+
"loss": 0.8711,
|
840 |
+
"step": 10700
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 94.12,
|
844 |
+
"learning_rate": 6.457446808510638e-06,
|
845 |
+
"loss": 0.8774,
|
846 |
+
"step": 10800
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 94.99,
|
850 |
+
"learning_rate": 5.393617021276596e-06,
|
851 |
+
"loss": 0.8781,
|
852 |
+
"step": 10900
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 95.86,
|
856 |
+
"learning_rate": 4.329787234042553e-06,
|
857 |
+
"loss": 0.8719,
|
858 |
+
"step": 11000
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 95.86,
|
862 |
+
"eval_loss": 0.22029033303260803,
|
863 |
+
"eval_runtime": 256.8466,
|
864 |
+
"eval_samples_per_second": 12.731,
|
865 |
+
"eval_steps_per_second": 1.592,
|
866 |
+
"eval_wer": 0.32705699280295664,
|
867 |
+
"step": 11000
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 96.73,
|
871 |
+
"learning_rate": 3.265957446808511e-06,
|
872 |
+
"loss": 0.8687,
|
873 |
+
"step": 11100
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 97.6,
|
877 |
+
"learning_rate": 2.2021276595744685e-06,
|
878 |
+
"loss": 0.8771,
|
879 |
+
"step": 11200
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 98.47,
|
883 |
+
"learning_rate": 1.1382978723404256e-06,
|
884 |
+
"loss": 0.8633,
|
885 |
+
"step": 11300
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 99.35,
|
889 |
+
"learning_rate": 7.446808510638299e-08,
|
890 |
+
"loss": 0.8779,
|
891 |
+
"step": 11400
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 99.35,
|
895 |
+
"step": 11400,
|
896 |
+
"total_flos": 1.353536402091675e+20,
|
897 |
+
"train_loss": 1.3810767638892458,
|
898 |
+
"train_runtime": 73797.3063,
|
899 |
+
"train_samples_per_second": 9.949,
|
900 |
+
"train_steps_per_second": 0.154
|
901 |
+
}
|
902 |
+
],
|
903 |
+
"logging_steps": 100,
|
904 |
+
"max_steps": 11400,
|
905 |
+
"num_train_epochs": 100,
|
906 |
+
"save_steps": 500,
|
907 |
+
"total_flos": 1.353536402091675e+20,
|
908 |
+
"trial_name": null,
|
909 |
+
"trial_params": null
|
910 |
+
}
|