End of training
Browse files- README.md +8 -4
- all_results.json +16 -0
- eval_results.json +10 -0
- train_results.json +9 -0
- trainer_state.json +1212 -0
README.md
CHANGED
@@ -1,8 +1,12 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: rinna/japanese-hubert-base
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
- wer
|
@@ -16,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# Hubert-common_voice_JSUT-ja-demo-japanese
|
18 |
|
19 |
-
This model is a fine-tuned version of [rinna/japanese-hubert-base](https://huggingface.co/rinna/japanese-hubert-base) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 2.
|
22 |
-
- Wer: 1.
|
23 |
-
- Cer: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
language:
|
4 |
+
- ja
|
5 |
license: apache-2.0
|
6 |
base_model: rinna/japanese-hubert-base
|
7 |
tags:
|
8 |
+
- automatic-speech-recognition
|
9 |
+
- mozilla-foundation/common_voice_13_0
|
10 |
- generated_from_trainer
|
11 |
metrics:
|
12 |
- wer
|
|
|
20 |
|
21 |
# Hubert-common_voice_JSUT-ja-demo-japanese
|
22 |
|
23 |
+
This model is a fine-tuned version of [rinna/japanese-hubert-base](https://huggingface.co/rinna/japanese-hubert-base) on the MOZILLA-FOUNDATION/COMMON_VOICE_13_0 - JA dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
+
- Loss: 2.1568
|
26 |
+
- Wer: 1.9920
|
27 |
+
- Cer: 0.6415
|
28 |
|
29 |
## Model description
|
30 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_cer": 0.6415434821104824,
|
4 |
+
"eval_loss": 2.1568174362182617,
|
5 |
+
"eval_runtime": 247.3136,
|
6 |
+
"eval_samples": 5461,
|
7 |
+
"eval_samples_per_second": 22.081,
|
8 |
+
"eval_steps_per_second": 2.762,
|
9 |
+
"eval_wer": 1.9919502378338823,
|
10 |
+
"total_flos": 1.4857862206321902e+19,
|
11 |
+
"train_loss": 15.407913101757057,
|
12 |
+
"train_runtime": 65838.1292,
|
13 |
+
"train_samples": 16532,
|
14 |
+
"train_samples_per_second": 5.022,
|
15 |
+
"train_steps_per_second": 0.157
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_cer": 0.6415434821104824,
|
4 |
+
"eval_loss": 2.1568174362182617,
|
5 |
+
"eval_runtime": 247.3136,
|
6 |
+
"eval_samples": 5461,
|
7 |
+
"eval_samples_per_second": 22.081,
|
8 |
+
"eval_steps_per_second": 2.762,
|
9 |
+
"eval_wer": 1.9919502378338823
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 1.4857862206321902e+19,
|
4 |
+
"train_loss": 15.407913101757057,
|
5 |
+
"train_runtime": 65838.1292,
|
6 |
+
"train_samples": 16532,
|
7 |
+
"train_samples_per_second": 5.022,
|
8 |
+
"train_steps_per_second": 0.157
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.176206588745117,
|
3 |
+
"best_model_checkpoint": "./Hubert-common_voice_JSUT-ja-demo-japanese/checkpoint-10300",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 10340,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.19342359767891681,
|
13 |
+
"eval_cer": 8.48504498730911,
|
14 |
+
"eval_loss": 84.69584655761719,
|
15 |
+
"eval_runtime": 236.8633,
|
16 |
+
"eval_samples_per_second": 23.055,
|
17 |
+
"eval_steps_per_second": 2.884,
|
18 |
+
"eval_wer": 1.0115257958287596,
|
19 |
+
"step": 100
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 0.38684719535783363,
|
23 |
+
"eval_cer": 8.344315240030694,
|
24 |
+
"eval_loss": 83.78863525390625,
|
25 |
+
"eval_runtime": 232.6848,
|
26 |
+
"eval_samples_per_second": 23.47,
|
27 |
+
"eval_steps_per_second": 2.935,
|
28 |
+
"eval_wer": 1.008964507866813,
|
29 |
+
"step": 200
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.5802707930367504,
|
33 |
+
"eval_cer": 4.815741763569977,
|
34 |
+
"eval_loss": 81.74565124511719,
|
35 |
+
"eval_runtime": 231.6247,
|
36 |
+
"eval_samples_per_second": 23.577,
|
37 |
+
"eval_steps_per_second": 2.949,
|
38 |
+
"eval_wer": 1.000365898280278,
|
39 |
+
"step": 300
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.7736943907156673,
|
43 |
+
"eval_cer": 0.9907074011923535,
|
44 |
+
"eval_loss": 75.43038940429688,
|
45 |
+
"eval_runtime": 227.0361,
|
46 |
+
"eval_samples_per_second": 24.053,
|
47 |
+
"eval_steps_per_second": 3.008,
|
48 |
+
"eval_wer": 1.0,
|
49 |
+
"step": 400
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.9671179883945842,
|
53 |
+
"grad_norm": 140.793212890625,
|
54 |
+
"learning_rate": 1.188e-06,
|
55 |
+
"loss": 66.0277,
|
56 |
+
"step": 500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.9671179883945842,
|
60 |
+
"eval_cer": 0.9907495636188854,
|
61 |
+
"eval_loss": 63.1251106262207,
|
62 |
+
"eval_runtime": 226.7903,
|
63 |
+
"eval_samples_per_second": 24.08,
|
64 |
+
"eval_steps_per_second": 3.012,
|
65 |
+
"eval_wer": 1.0,
|
66 |
+
"step": 500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.1605415860735009,
|
70 |
+
"eval_cer": 0.9907074011923535,
|
71 |
+
"eval_loss": 57.10499572753906,
|
72 |
+
"eval_runtime": 255.6303,
|
73 |
+
"eval_samples_per_second": 21.363,
|
74 |
+
"eval_steps_per_second": 2.672,
|
75 |
+
"eval_wer": 1.0,
|
76 |
+
"step": 600
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.3539651837524178,
|
80 |
+
"eval_cer": 0.9907917260454173,
|
81 |
+
"eval_loss": 55.67994689941406,
|
82 |
+
"eval_runtime": 269.8181,
|
83 |
+
"eval_samples_per_second": 20.24,
|
84 |
+
"eval_steps_per_second": 2.531,
|
85 |
+
"eval_wer": 1.0,
|
86 |
+
"step": 700
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.5473887814313345,
|
90 |
+
"eval_cer": 0.9907495636188854,
|
91 |
+
"eval_loss": 55.04756546020508,
|
92 |
+
"eval_runtime": 241.9741,
|
93 |
+
"eval_samples_per_second": 22.569,
|
94 |
+
"eval_steps_per_second": 2.823,
|
95 |
+
"eval_wer": 1.0,
|
96 |
+
"step": 800
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.7408123791102514,
|
100 |
+
"eval_cer": 0.9907074011923535,
|
101 |
+
"eval_loss": 54.408546447753906,
|
102 |
+
"eval_runtime": 256.9455,
|
103 |
+
"eval_samples_per_second": 21.254,
|
104 |
+
"eval_steps_per_second": 2.658,
|
105 |
+
"eval_wer": 1.0,
|
106 |
+
"step": 900
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.9342359767891684,
|
110 |
+
"grad_norm": 141.13522338867188,
|
111 |
+
"learning_rate": 2.3855999999999997e-06,
|
112 |
+
"loss": 46.3141,
|
113 |
+
"step": 1000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.9342359767891684,
|
117 |
+
"eval_cer": 0.9907917260454173,
|
118 |
+
"eval_loss": 53.68925857543945,
|
119 |
+
"eval_runtime": 260.4063,
|
120 |
+
"eval_samples_per_second": 20.971,
|
121 |
+
"eval_steps_per_second": 2.623,
|
122 |
+
"eval_wer": 1.0,
|
123 |
+
"step": 1000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.127659574468085,
|
127 |
+
"eval_cer": 0.9907074011923535,
|
128 |
+
"eval_loss": 52.97110366821289,
|
129 |
+
"eval_runtime": 254.697,
|
130 |
+
"eval_samples_per_second": 21.441,
|
131 |
+
"eval_steps_per_second": 2.682,
|
132 |
+
"eval_wer": 1.0,
|
133 |
+
"step": 1100
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 2.3210831721470018,
|
137 |
+
"eval_cer": 0.9907495636188854,
|
138 |
+
"eval_loss": 52.13261032104492,
|
139 |
+
"eval_runtime": 246.5799,
|
140 |
+
"eval_samples_per_second": 22.147,
|
141 |
+
"eval_steps_per_second": 2.77,
|
142 |
+
"eval_wer": 1.0,
|
143 |
+
"step": 1200
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.514506769825919,
|
147 |
+
"eval_cer": 0.9907074011923535,
|
148 |
+
"eval_loss": 51.254920959472656,
|
149 |
+
"eval_runtime": 260.2756,
|
150 |
+
"eval_samples_per_second": 20.982,
|
151 |
+
"eval_steps_per_second": 2.624,
|
152 |
+
"eval_wer": 1.0,
|
153 |
+
"step": 1300
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 2.7079303675048356,
|
157 |
+
"eval_cer": 0.9907074011923535,
|
158 |
+
"eval_loss": 50.26494598388672,
|
159 |
+
"eval_runtime": 261.2096,
|
160 |
+
"eval_samples_per_second": 20.907,
|
161 |
+
"eval_steps_per_second": 2.615,
|
162 |
+
"eval_wer": 1.0,
|
163 |
+
"step": 1400
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.9013539651837523,
|
167 |
+
"grad_norm": 120.8663101196289,
|
168 |
+
"learning_rate": 3.5856e-06,
|
169 |
+
"loss": 42.8642,
|
170 |
+
"step": 1500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.9013539651837523,
|
174 |
+
"eval_cer": 0.9907074011923535,
|
175 |
+
"eval_loss": 49.20811080932617,
|
176 |
+
"eval_runtime": 258.4268,
|
177 |
+
"eval_samples_per_second": 21.132,
|
178 |
+
"eval_steps_per_second": 2.643,
|
179 |
+
"eval_wer": 1.0,
|
180 |
+
"step": 1500
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.094777562862669,
|
184 |
+
"eval_cer": 0.9907495636188854,
|
185 |
+
"eval_loss": 48.105064392089844,
|
186 |
+
"eval_runtime": 247.347,
|
187 |
+
"eval_samples_per_second": 22.078,
|
188 |
+
"eval_steps_per_second": 2.761,
|
189 |
+
"eval_wer": 1.0,
|
190 |
+
"step": 1600
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 3.288201160541586,
|
194 |
+
"eval_cer": 0.9907074011923535,
|
195 |
+
"eval_loss": 46.87884521484375,
|
196 |
+
"eval_runtime": 262.3223,
|
197 |
+
"eval_samples_per_second": 20.818,
|
198 |
+
"eval_steps_per_second": 2.604,
|
199 |
+
"eval_wer": 1.0,
|
200 |
+
"step": 1700
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 3.481624758220503,
|
204 |
+
"eval_cer": 0.9907074011923535,
|
205 |
+
"eval_loss": 45.54108810424805,
|
206 |
+
"eval_runtime": 228.7269,
|
207 |
+
"eval_samples_per_second": 23.876,
|
208 |
+
"eval_steps_per_second": 2.986,
|
209 |
+
"eval_wer": 1.0,
|
210 |
+
"step": 1800
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 3.6750483558994196,
|
214 |
+
"eval_cer": 0.9907074011923535,
|
215 |
+
"eval_loss": 44.151554107666016,
|
216 |
+
"eval_runtime": 228.7844,
|
217 |
+
"eval_samples_per_second": 23.87,
|
218 |
+
"eval_steps_per_second": 2.985,
|
219 |
+
"eval_wer": 1.0,
|
220 |
+
"step": 1900
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 3.8684719535783367,
|
224 |
+
"grad_norm": 172.9249725341797,
|
225 |
+
"learning_rate": 4.7856e-06,
|
226 |
+
"loss": 38.3378,
|
227 |
+
"step": 2000
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 3.8684719535783367,
|
231 |
+
"eval_cer": 0.9907495636188854,
|
232 |
+
"eval_loss": 42.60865783691406,
|
233 |
+
"eval_runtime": 227.6693,
|
234 |
+
"eval_samples_per_second": 23.987,
|
235 |
+
"eval_steps_per_second": 3.0,
|
236 |
+
"eval_wer": 1.0,
|
237 |
+
"step": 2000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 4.061895551257253,
|
241 |
+
"eval_cer": 0.9907074011923535,
|
242 |
+
"eval_loss": 40.9814567565918,
|
243 |
+
"eval_runtime": 230.7363,
|
244 |
+
"eval_samples_per_second": 23.668,
|
245 |
+
"eval_steps_per_second": 2.96,
|
246 |
+
"eval_wer": 1.0,
|
247 |
+
"step": 2100
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 4.25531914893617,
|
251 |
+
"eval_cer": 0.9907074011923535,
|
252 |
+
"eval_loss": 39.240055084228516,
|
253 |
+
"eval_runtime": 230.4939,
|
254 |
+
"eval_samples_per_second": 23.693,
|
255 |
+
"eval_steps_per_second": 2.963,
|
256 |
+
"eval_wer": 1.0,
|
257 |
+
"step": 2200
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 4.448742746615087,
|
261 |
+
"eval_cer": 0.9907917260454173,
|
262 |
+
"eval_loss": 37.40217590332031,
|
263 |
+
"eval_runtime": 228.8585,
|
264 |
+
"eval_samples_per_second": 23.862,
|
265 |
+
"eval_steps_per_second": 2.984,
|
266 |
+
"eval_wer": 1.0,
|
267 |
+
"step": 2300
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 4.6421663442940035,
|
271 |
+
"eval_cer": 0.9907495636188854,
|
272 |
+
"eval_loss": 35.430931091308594,
|
273 |
+
"eval_runtime": 229.2781,
|
274 |
+
"eval_samples_per_second": 23.818,
|
275 |
+
"eval_steps_per_second": 2.979,
|
276 |
+
"eval_wer": 1.0,
|
277 |
+
"step": 2400
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 4.835589941972921,
|
281 |
+
"grad_norm": 113.81422424316406,
|
282 |
+
"learning_rate": 5.9856e-06,
|
283 |
+
"loss": 31.9192,
|
284 |
+
"step": 2500
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 4.835589941972921,
|
288 |
+
"eval_cer": 0.9907074011923535,
|
289 |
+
"eval_loss": 33.417510986328125,
|
290 |
+
"eval_runtime": 233.5128,
|
291 |
+
"eval_samples_per_second": 23.386,
|
292 |
+
"eval_steps_per_second": 2.925,
|
293 |
+
"eval_wer": 1.0,
|
294 |
+
"step": 2500
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 5.029013539651838,
|
298 |
+
"eval_cer": 0.9907495636188854,
|
299 |
+
"eval_loss": 31.266008377075195,
|
300 |
+
"eval_runtime": 235.6664,
|
301 |
+
"eval_samples_per_second": 23.173,
|
302 |
+
"eval_steps_per_second": 2.898,
|
303 |
+
"eval_wer": 1.0,
|
304 |
+
"step": 2600
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 5.222437137330754,
|
308 |
+
"eval_cer": 0.9907917260454173,
|
309 |
+
"eval_loss": 29.01472282409668,
|
310 |
+
"eval_runtime": 238.0062,
|
311 |
+
"eval_samples_per_second": 22.945,
|
312 |
+
"eval_steps_per_second": 2.87,
|
313 |
+
"eval_wer": 1.0,
|
314 |
+
"step": 2700
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 5.415860735009671,
|
318 |
+
"eval_cer": 0.9907495636188854,
|
319 |
+
"eval_loss": 26.68852996826172,
|
320 |
+
"eval_runtime": 267.9224,
|
321 |
+
"eval_samples_per_second": 20.383,
|
322 |
+
"eval_steps_per_second": 2.549,
|
323 |
+
"eval_wer": 1.0,
|
324 |
+
"step": 2800
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 5.609284332688588,
|
328 |
+
"eval_cer": 0.9907495636188854,
|
329 |
+
"eval_loss": 24.301000595092773,
|
330 |
+
"eval_runtime": 235.2693,
|
331 |
+
"eval_samples_per_second": 23.212,
|
332 |
+
"eval_steps_per_second": 2.903,
|
333 |
+
"eval_wer": 1.0,
|
334 |
+
"step": 2900
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 5.802707930367505,
|
338 |
+
"grad_norm": 106.30471801757812,
|
339 |
+
"learning_rate": 7.1856e-06,
|
340 |
+
"loss": 23.4284,
|
341 |
+
"step": 3000
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 5.802707930367505,
|
345 |
+
"eval_cer": 0.9907495636188854,
|
346 |
+
"eval_loss": 21.88077735900879,
|
347 |
+
"eval_runtime": 232.75,
|
348 |
+
"eval_samples_per_second": 23.463,
|
349 |
+
"eval_steps_per_second": 2.934,
|
350 |
+
"eval_wer": 1.0,
|
351 |
+
"step": 3000
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 5.996131528046422,
|
355 |
+
"eval_cer": 0.9907917260454173,
|
356 |
+
"eval_loss": 19.473451614379883,
|
357 |
+
"eval_runtime": 233.7728,
|
358 |
+
"eval_samples_per_second": 23.36,
|
359 |
+
"eval_steps_per_second": 2.922,
|
360 |
+
"eval_wer": 1.0,
|
361 |
+
"step": 3100
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 6.189555125725338,
|
365 |
+
"eval_cer": 0.9908760508984813,
|
366 |
+
"eval_loss": 17.129289627075195,
|
367 |
+
"eval_runtime": 240.7161,
|
368 |
+
"eval_samples_per_second": 22.686,
|
369 |
+
"eval_steps_per_second": 2.837,
|
370 |
+
"eval_wer": 1.0,
|
371 |
+
"step": 3200
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 6.382978723404255,
|
375 |
+
"eval_cer": 0.9907917260454173,
|
376 |
+
"eval_loss": 14.863801002502441,
|
377 |
+
"eval_runtime": 233.6375,
|
378 |
+
"eval_samples_per_second": 23.374,
|
379 |
+
"eval_steps_per_second": 2.923,
|
380 |
+
"eval_wer": 1.0,
|
381 |
+
"step": 3300
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 6.576402321083172,
|
385 |
+
"eval_cer": 0.9907074011923535,
|
386 |
+
"eval_loss": 12.806206703186035,
|
387 |
+
"eval_runtime": 251.782,
|
388 |
+
"eval_samples_per_second": 21.689,
|
389 |
+
"eval_steps_per_second": 2.713,
|
390 |
+
"eval_wer": 1.0,
|
391 |
+
"step": 3400
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 6.769825918762089,
|
395 |
+
"grad_norm": 82.23467254638672,
|
396 |
+
"learning_rate": 8.3856e-06,
|
397 |
+
"loss": 13.9431,
|
398 |
+
"step": 3500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 6.769825918762089,
|
402 |
+
"eval_cer": 0.9907074011923535,
|
403 |
+
"eval_loss": 10.964253425598145,
|
404 |
+
"eval_runtime": 233.2904,
|
405 |
+
"eval_samples_per_second": 23.409,
|
406 |
+
"eval_steps_per_second": 2.928,
|
407 |
+
"eval_wer": 1.0,
|
408 |
+
"step": 3500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 6.963249516441006,
|
412 |
+
"eval_cer": 0.9907495636188854,
|
413 |
+
"eval_loss": 9.411906242370605,
|
414 |
+
"eval_runtime": 235.0547,
|
415 |
+
"eval_samples_per_second": 23.233,
|
416 |
+
"eval_steps_per_second": 2.906,
|
417 |
+
"eval_wer": 1.0,
|
418 |
+
"step": 3600
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 7.156673114119923,
|
422 |
+
"eval_cer": 0.9907495636188854,
|
423 |
+
"eval_loss": 8.164007186889648,
|
424 |
+
"eval_runtime": 287.0729,
|
425 |
+
"eval_samples_per_second": 19.023,
|
426 |
+
"eval_steps_per_second": 2.379,
|
427 |
+
"eval_wer": 1.0,
|
428 |
+
"step": 3700
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 7.350096711798839,
|
432 |
+
"eval_cer": 0.9907495636188854,
|
433 |
+
"eval_loss": 7.22973108291626,
|
434 |
+
"eval_runtime": 237.3392,
|
435 |
+
"eval_samples_per_second": 23.009,
|
436 |
+
"eval_steps_per_second": 2.878,
|
437 |
+
"eval_wer": 1.0,
|
438 |
+
"step": 3800
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 7.543520309477756,
|
442 |
+
"eval_cer": 0.9907074011923535,
|
443 |
+
"eval_loss": 6.571568489074707,
|
444 |
+
"eval_runtime": 232.6033,
|
445 |
+
"eval_samples_per_second": 23.478,
|
446 |
+
"eval_steps_per_second": 2.936,
|
447 |
+
"eval_wer": 1.0,
|
448 |
+
"step": 3900
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 7.7369439071566735,
|
452 |
+
"grad_norm": 4.932778358459473,
|
453 |
+
"learning_rate": 9.585600000000002e-06,
|
454 |
+
"loss": 7.4585,
|
455 |
+
"step": 4000
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 7.7369439071566735,
|
459 |
+
"eval_cer": 0.9907495636188854,
|
460 |
+
"eval_loss": 6.141250133514404,
|
461 |
+
"eval_runtime": 234.2968,
|
462 |
+
"eval_samples_per_second": 23.308,
|
463 |
+
"eval_steps_per_second": 2.915,
|
464 |
+
"eval_wer": 1.0,
|
465 |
+
"step": 4000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 7.93036750483559,
|
469 |
+
"eval_cer": 0.9907074011923535,
|
470 |
+
"eval_loss": 5.885389804840088,
|
471 |
+
"eval_runtime": 236.1436,
|
472 |
+
"eval_samples_per_second": 23.126,
|
473 |
+
"eval_steps_per_second": 2.892,
|
474 |
+
"eval_wer": 1.0,
|
475 |
+
"step": 4100
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 8.123791102514506,
|
479 |
+
"eval_cer": 0.9907495636188854,
|
480 |
+
"eval_loss": 5.770660877227783,
|
481 |
+
"eval_runtime": 234.5762,
|
482 |
+
"eval_samples_per_second": 23.28,
|
483 |
+
"eval_steps_per_second": 2.912,
|
484 |
+
"eval_wer": 1.0,
|
485 |
+
"step": 4200
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 8.317214700193423,
|
489 |
+
"eval_cer": 0.9907074011923535,
|
490 |
+
"eval_loss": 5.680200576782227,
|
491 |
+
"eval_runtime": 231.827,
|
492 |
+
"eval_samples_per_second": 23.556,
|
493 |
+
"eval_steps_per_second": 2.946,
|
494 |
+
"eval_wer": 1.0,
|
495 |
+
"step": 4300
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 8.51063829787234,
|
499 |
+
"eval_cer": 0.9907495636188854,
|
500 |
+
"eval_loss": 5.597055435180664,
|
501 |
+
"eval_runtime": 232.7784,
|
502 |
+
"eval_samples_per_second": 23.46,
|
503 |
+
"eval_steps_per_second": 2.934,
|
504 |
+
"eval_wer": 1.0,
|
505 |
+
"step": 4400
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 8.704061895551257,
|
509 |
+
"grad_norm": 1.6451424360275269,
|
510 |
+
"learning_rate": 1.07856e-05,
|
511 |
+
"loss": 5.7398,
|
512 |
+
"step": 4500
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 8.704061895551257,
|
516 |
+
"eval_cer": 0.9907495636188854,
|
517 |
+
"eval_loss": 5.533324241638184,
|
518 |
+
"eval_runtime": 232.5892,
|
519 |
+
"eval_samples_per_second": 23.479,
|
520 |
+
"eval_steps_per_second": 2.937,
|
521 |
+
"eval_wer": 1.0,
|
522 |
+
"step": 4500
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 8.897485493230175,
|
526 |
+
"eval_cer": 0.9907074011923535,
|
527 |
+
"eval_loss": 5.475062370300293,
|
528 |
+
"eval_runtime": 233.1057,
|
529 |
+
"eval_samples_per_second": 23.427,
|
530 |
+
"eval_steps_per_second": 2.93,
|
531 |
+
"eval_wer": 1.0,
|
532 |
+
"step": 4600
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 9.090909090909092,
|
536 |
+
"eval_cer": 0.9907495636188854,
|
537 |
+
"eval_loss": 5.425434589385986,
|
538 |
+
"eval_runtime": 232.7779,
|
539 |
+
"eval_samples_per_second": 23.46,
|
540 |
+
"eval_steps_per_second": 2.934,
|
541 |
+
"eval_wer": 1.0,
|
542 |
+
"step": 4700
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 9.284332688588007,
|
546 |
+
"eval_cer": 0.9908423209572558,
|
547 |
+
"eval_loss": 5.377471923828125,
|
548 |
+
"eval_runtime": 234.4379,
|
549 |
+
"eval_samples_per_second": 23.294,
|
550 |
+
"eval_steps_per_second": 2.913,
|
551 |
+
"eval_wer": 1.1319063300402488,
|
552 |
+
"step": 4800
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 9.477756286266924,
|
556 |
+
"eval_cer": 0.9907495636188854,
|
557 |
+
"eval_loss": 5.343258380889893,
|
558 |
+
"eval_runtime": 239.0036,
|
559 |
+
"eval_samples_per_second": 22.849,
|
560 |
+
"eval_steps_per_second": 2.858,
|
561 |
+
"eval_wer": 1.33205268935236,
|
562 |
+
"step": 4900
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 9.671179883945841,
|
566 |
+
"grad_norm": 2.292585611343384,
|
567 |
+
"learning_rate": 1.19856e-05,
|
568 |
+
"loss": 5.4159,
|
569 |
+
"step": 5000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 9.671179883945841,
|
573 |
+
"eval_cer": 0.9906146438539831,
|
574 |
+
"eval_loss": 5.311874866485596,
|
575 |
+
"eval_runtime": 235.3723,
|
576 |
+
"eval_samples_per_second": 23.202,
|
577 |
+
"eval_steps_per_second": 2.902,
|
578 |
+
"eval_wer": 1.686242224661544,
|
579 |
+
"step": 5000
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 9.864603481624759,
|
583 |
+
"eval_cer": 0.9909688082368516,
|
584 |
+
"eval_loss": 5.269064426422119,
|
585 |
+
"eval_runtime": 234.5017,
|
586 |
+
"eval_samples_per_second": 23.288,
|
587 |
+
"eval_steps_per_second": 2.913,
|
588 |
+
"eval_wer": 1.4255396999634102,
|
589 |
+
"step": 5100
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 10.058027079303676,
|
593 |
+
"eval_cer": 0.9909182133250133,
|
594 |
+
"eval_loss": 5.236879825592041,
|
595 |
+
"eval_runtime": 235.3148,
|
596 |
+
"eval_samples_per_second": 23.207,
|
597 |
+
"eval_steps_per_second": 2.902,
|
598 |
+
"eval_wer": 1.4043175997072814,
|
599 |
+
"step": 5200
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 10.251450676982591,
|
603 |
+
"eval_cer": 0.9909603757515453,
|
604 |
+
"eval_loss": 5.194947719573975,
|
605 |
+
"eval_runtime": 232.4545,
|
606 |
+
"eval_samples_per_second": 23.493,
|
607 |
+
"eval_steps_per_second": 2.938,
|
608 |
+
"eval_wer": 1.5686059275521405,
|
609 |
+
"step": 5300
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 10.444874274661508,
|
613 |
+
"eval_cer": 0.9908170235013366,
|
614 |
+
"eval_loss": 5.151918888092041,
|
615 |
+
"eval_runtime": 231.5581,
|
616 |
+
"eval_samples_per_second": 23.584,
|
617 |
+
"eval_steps_per_second": 2.95,
|
618 |
+
"eval_wer": 1.5166483717526527,
|
619 |
+
"step": 5400
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 10.638297872340425,
|
623 |
+
"grad_norm": 2.0632503032684326,
|
624 |
+
"learning_rate": 1.3185600000000001e-05,
|
625 |
+
"loss": 5.2163,
|
626 |
+
"step": 5500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 10.638297872340425,
|
630 |
+
"eval_cer": 0.9909603757515453,
|
631 |
+
"eval_loss": 5.108114242553711,
|
632 |
+
"eval_runtime": 232.6627,
|
633 |
+
"eval_samples_per_second": 23.472,
|
634 |
+
"eval_steps_per_second": 2.936,
|
635 |
+
"eval_wer": 1.247713135748262,
|
636 |
+
"step": 5500
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 10.831721470019342,
|
640 |
+
"eval_cer": 0.9907664285894981,
|
641 |
+
"eval_loss": 5.055335998535156,
|
642 |
+
"eval_runtime": 231.9668,
|
643 |
+
"eval_samples_per_second": 23.542,
|
644 |
+
"eval_steps_per_second": 2.944,
|
645 |
+
"eval_wer": 1.5124405415294548,
|
646 |
+
"step": 5600
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 11.02514506769826,
|
650 |
+
"eval_cer": 0.9908760508984813,
|
651 |
+
"eval_loss": 5.012271881103516,
|
652 |
+
"eval_runtime": 231.643,
|
653 |
+
"eval_samples_per_second": 23.575,
|
654 |
+
"eval_steps_per_second": 2.949,
|
655 |
+
"eval_wer": 1.5495792169776803,
|
656 |
+
"step": 5700
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 11.218568665377177,
|
660 |
+
"eval_cer": 0.9885824148951421,
|
661 |
+
"eval_loss": 4.942389965057373,
|
662 |
+
"eval_runtime": 232.3058,
|
663 |
+
"eval_samples_per_second": 23.508,
|
664 |
+
"eval_steps_per_second": 2.94,
|
665 |
+
"eval_wer": 1.7621661178192463,
|
666 |
+
"step": 5800
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 11.411992263056092,
|
670 |
+
"eval_cer": 0.9830675695047602,
|
671 |
+
"eval_loss": 4.8753485679626465,
|
672 |
+
"eval_runtime": 233.7911,
|
673 |
+
"eval_samples_per_second": 23.358,
|
674 |
+
"eval_steps_per_second": 2.921,
|
675 |
+
"eval_wer": 1.5404317599707282,
|
676 |
+
"step": 5900
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 11.60541586073501,
|
680 |
+
"grad_norm": 1.9146788120269775,
|
681 |
+
"learning_rate": 1.43856e-05,
|
682 |
+
"loss": 4.9465,
|
683 |
+
"step": 6000
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 11.60541586073501,
|
687 |
+
"eval_cer": 0.9749808160959279,
|
688 |
+
"eval_loss": 4.77677059173584,
|
689 |
+
"eval_runtime": 232.0203,
|
690 |
+
"eval_samples_per_second": 23.537,
|
691 |
+
"eval_steps_per_second": 2.944,
|
692 |
+
"eval_wer": 1.853457738748628,
|
693 |
+
"step": 6000
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 11.798839458413926,
|
697 |
+
"eval_cer": 0.9713126849876464,
|
698 |
+
"eval_loss": 4.6841044425964355,
|
699 |
+
"eval_runtime": 231.7273,
|
700 |
+
"eval_samples_per_second": 23.566,
|
701 |
+
"eval_steps_per_second": 2.947,
|
702 |
+
"eval_wer": 1.8395536040980607,
|
703 |
+
"step": 6100
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 11.992263056092844,
|
707 |
+
"eval_cer": 0.9697020802941251,
|
708 |
+
"eval_loss": 4.582820892333984,
|
709 |
+
"eval_runtime": 232.9124,
|
710 |
+
"eval_samples_per_second": 23.447,
|
711 |
+
"eval_steps_per_second": 2.932,
|
712 |
+
"eval_wer": 1.7444200512257593,
|
713 |
+
"step": 6200
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 12.18568665377176,
|
717 |
+
"eval_cer": 0.968909426675324,
|
718 |
+
"eval_loss": 4.485307693481445,
|
719 |
+
"eval_runtime": 232.9842,
|
720 |
+
"eval_samples_per_second": 23.439,
|
721 |
+
"eval_steps_per_second": 2.932,
|
722 |
+
"eval_wer": 1.801317233809001,
|
723 |
+
"step": 6300
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 12.379110251450676,
|
727 |
+
"eval_cer": 0.9556029648618337,
|
728 |
+
"eval_loss": 4.395504951477051,
|
729 |
+
"eval_runtime": 233.0172,
|
730 |
+
"eval_samples_per_second": 23.436,
|
731 |
+
"eval_steps_per_second": 2.931,
|
732 |
+
"eval_wer": 1.827844859129162,
|
733 |
+
"step": 6400
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 12.572533849129593,
|
737 |
+
"grad_norm": 4.459765434265137,
|
738 |
+
"learning_rate": 1.55856e-05,
|
739 |
+
"loss": 4.5094,
|
740 |
+
"step": 6500
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 12.572533849129593,
|
744 |
+
"eval_cer": 0.9123021528134987,
|
745 |
+
"eval_loss": 4.284241676330566,
|
746 |
+
"eval_runtime": 230.5488,
|
747 |
+
"eval_samples_per_second": 23.687,
|
748 |
+
"eval_steps_per_second": 2.962,
|
749 |
+
"eval_wer": 1.8728503476033662,
|
750 |
+
"step": 6500
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 12.76595744680851,
|
754 |
+
"eval_cer": 0.8650380726711584,
|
755 |
+
"eval_loss": 4.181938171386719,
|
756 |
+
"eval_runtime": 232.0403,
|
757 |
+
"eval_samples_per_second": 23.535,
|
758 |
+
"eval_steps_per_second": 2.943,
|
759 |
+
"eval_wer": 1.9094401756311745,
|
760 |
+
"step": 6600
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 12.959381044487428,
|
764 |
+
"eval_cer": 0.848628456264915,
|
765 |
+
"eval_loss": 4.074057579040527,
|
766 |
+
"eval_runtime": 231.4468,
|
767 |
+
"eval_samples_per_second": 23.595,
|
768 |
+
"eval_steps_per_second": 2.951,
|
769 |
+
"eval_wer": 1.9134650567142335,
|
770 |
+
"step": 6700
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 13.152804642166345,
|
774 |
+
"eval_cer": 0.8385937987503057,
|
775 |
+
"eval_loss": 3.9648523330688477,
|
776 |
+
"eval_runtime": 231.3067,
|
777 |
+
"eval_samples_per_second": 23.609,
|
778 |
+
"eval_steps_per_second": 2.953,
|
779 |
+
"eval_wer": 1.9191364800585438,
|
780 |
+
"step": 6800
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 13.346228239845262,
|
784 |
+
"eval_cer": 0.8189292430157941,
|
785 |
+
"eval_loss": 3.8640658855438232,
|
786 |
+
"eval_runtime": 237.0711,
|
787 |
+
"eval_samples_per_second": 23.035,
|
788 |
+
"eval_steps_per_second": 2.881,
|
789 |
+
"eval_wer": 1.9195023783388219,
|
790 |
+
"step": 6900
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 13.539651837524177,
|
794 |
+
"grad_norm": 4.586193084716797,
|
795 |
+
"learning_rate": 1.67856e-05,
|
796 |
+
"loss": 4.0097,
|
797 |
+
"step": 7000
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 13.539651837524177,
|
801 |
+
"eval_cer": 0.8014487009756386,
|
802 |
+
"eval_loss": 3.7686750888824463,
|
803 |
+
"eval_runtime": 244.328,
|
804 |
+
"eval_samples_per_second": 22.351,
|
805 |
+
"eval_steps_per_second": 2.795,
|
806 |
+
"eval_wer": 1.9275521405049396,
|
807 |
+
"step": 7000
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 13.733075435203094,
|
811 |
+
"eval_cer": 0.7963301823946571,
|
812 |
+
"eval_loss": 3.680776596069336,
|
813 |
+
"eval_runtime": 230.3109,
|
814 |
+
"eval_samples_per_second": 23.711,
|
815 |
+
"eval_steps_per_second": 2.966,
|
816 |
+
"eval_wer": 1.9259055982436883,
|
817 |
+
"step": 7100
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 13.926499032882012,
|
821 |
+
"eval_cer": 0.779220669707983,
|
822 |
+
"eval_loss": 3.60208797454834,
|
823 |
+
"eval_runtime": 229.5487,
|
824 |
+
"eval_samples_per_second": 23.79,
|
825 |
+
"eval_steps_per_second": 2.975,
|
826 |
+
"eval_wer": 1.9275521405049396,
|
827 |
+
"step": 7200
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 14.119922630560929,
|
831 |
+
"eval_cer": 0.777466712764253,
|
832 |
+
"eval_loss": 3.55332088470459,
|
833 |
+
"eval_runtime": 231.4776,
|
834 |
+
"eval_samples_per_second": 23.592,
|
835 |
+
"eval_steps_per_second": 2.951,
|
836 |
+
"eval_wer": 1.9366995975118917,
|
837 |
+
"step": 7300
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 14.313346228239846,
|
841 |
+
"eval_cer": 0.775071886937237,
|
842 |
+
"eval_loss": 3.476841449737549,
|
843 |
+
"eval_runtime": 240.5885,
|
844 |
+
"eval_samples_per_second": 22.699,
|
845 |
+
"eval_steps_per_second": 2.839,
|
846 |
+
"eval_wer": 1.9321258690084158,
|
847 |
+
"step": 7400
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 14.506769825918763,
|
851 |
+
"grad_norm": 4.310749053955078,
|
852 |
+
"learning_rate": 1.7985600000000003e-05,
|
853 |
+
"loss": 3.5619,
|
854 |
+
"step": 7500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 14.506769825918763,
|
858 |
+
"eval_cer": 0.7672043781463711,
|
859 |
+
"eval_loss": 3.4284844398498535,
|
860 |
+
"eval_runtime": 240.9512,
|
861 |
+
"eval_samples_per_second": 22.664,
|
862 |
+
"eval_steps_per_second": 2.835,
|
863 |
+
"eval_wer": 1.938529088913282,
|
864 |
+
"step": 7500
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 14.700193423597678,
|
868 |
+
"eval_cer": 0.7659816677769439,
|
869 |
+
"eval_loss": 3.362793445587158,
|
870 |
+
"eval_runtime": 230.1401,
|
871 |
+
"eval_samples_per_second": 23.729,
|
872 |
+
"eval_steps_per_second": 2.968,
|
873 |
+
"eval_wer": 1.9361507500914745,
|
874 |
+
"step": 7600
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 14.893617021276595,
|
878 |
+
"eval_cer": 0.7618919124033426,
|
879 |
+
"eval_loss": 3.2909657955169678,
|
880 |
+
"eval_runtime": 233.6336,
|
881 |
+
"eval_samples_per_second": 23.374,
|
882 |
+
"eval_steps_per_second": 2.923,
|
883 |
+
"eval_wer": 1.9313940724478595,
|
884 |
+
"step": 7700
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 15.087040618955513,
|
888 |
+
"eval_cer": 0.7486360455016907,
|
889 |
+
"eval_loss": 3.2242627143859863,
|
890 |
+
"eval_runtime": 241.9894,
|
891 |
+
"eval_samples_per_second": 22.567,
|
892 |
+
"eval_steps_per_second": 2.822,
|
893 |
+
"eval_wer": 1.928832784485913,
|
894 |
+
"step": 7800
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 15.28046421663443,
|
898 |
+
"eval_cer": 0.7431802275084536,
|
899 |
+
"eval_loss": 3.164518117904663,
|
900 |
+
"eval_runtime": 232.2322,
|
901 |
+
"eval_samples_per_second": 23.515,
|
902 |
+
"eval_steps_per_second": 2.941,
|
903 |
+
"eval_wer": 1.9308452250274424,
|
904 |
+
"step": 7900
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 15.473887814313347,
|
908 |
+
"grad_norm": 5.67767333984375,
|
909 |
+
"learning_rate": 1.91856e-05,
|
910 |
+
"loss": 3.2379,
|
911 |
+
"step": 8000
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 15.473887814313347,
|
915 |
+
"eval_cer": 0.7382556560895193,
|
916 |
+
"eval_loss": 3.1185944080352783,
|
917 |
+
"eval_runtime": 235.8886,
|
918 |
+
"eval_samples_per_second": 23.151,
|
919 |
+
"eval_steps_per_second": 2.895,
|
920 |
+
"eval_wer": 1.9332235638492499,
|
921 |
+
"step": 8000
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 15.667311411992262,
|
925 |
+
"eval_cer": 0.7374714349560246,
|
926 |
+
"eval_loss": 3.078275203704834,
|
927 |
+
"eval_runtime": 234.7574,
|
928 |
+
"eval_samples_per_second": 23.262,
|
929 |
+
"eval_steps_per_second": 2.909,
|
930 |
+
"eval_wer": 1.9348701061105014,
|
931 |
+
"step": 8100
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 15.86073500967118,
|
935 |
+
"eval_cer": 0.727942726559799,
|
936 |
+
"eval_loss": 3.0145950317382812,
|
937 |
+
"eval_runtime": 231.4339,
|
938 |
+
"eval_samples_per_second": 23.596,
|
939 |
+
"eval_steps_per_second": 2.951,
|
940 |
+
"eval_wer": 1.9321258690084158,
|
941 |
+
"step": 8200
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 16.054158607350097,
|
945 |
+
"eval_cer": 0.7300086854598656,
|
946 |
+
"eval_loss": 2.9523487091064453,
|
947 |
+
"eval_runtime": 235.1315,
|
948 |
+
"eval_samples_per_second": 23.225,
|
949 |
+
"eval_steps_per_second": 2.905,
|
950 |
+
"eval_wer": 1.9308452250274424,
|
951 |
+
"step": 8300
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 16.247582205029012,
|
955 |
+
"eval_cer": 0.7254467109091063,
|
956 |
+
"eval_loss": 2.918687105178833,
|
957 |
+
"eval_runtime": 238.3374,
|
958 |
+
"eval_samples_per_second": 22.913,
|
959 |
+
"eval_steps_per_second": 2.866,
|
960 |
+
"eval_wer": 1.9273691913648006,
|
961 |
+
"step": 8400
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 16.44100580270793,
|
965 |
+
"grad_norm": 8.755329132080078,
|
966 |
+
"learning_rate": 2.03856e-05,
|
967 |
+
"loss": 2.9448,
|
968 |
+
"step": 8500
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 16.44100580270793,
|
972 |
+
"eval_cer": 0.7177394193390618,
|
973 |
+
"eval_loss": 2.8671371936798096,
|
974 |
+
"eval_runtime": 229.0989,
|
975 |
+
"eval_samples_per_second": 23.837,
|
976 |
+
"eval_steps_per_second": 2.981,
|
977 |
+
"eval_wer": 1.929015733626052,
|
978 |
+
"step": 8500
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 16.634429400386846,
|
982 |
+
"eval_cer": 0.7115752725800876,
|
983 |
+
"eval_loss": 2.8188540935516357,
|
984 |
+
"eval_runtime": 230.6192,
|
985 |
+
"eval_samples_per_second": 23.68,
|
986 |
+
"eval_steps_per_second": 2.962,
|
987 |
+
"eval_wer": 1.9348701061105014,
|
988 |
+
"step": 8600
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 16.827852998065765,
|
992 |
+
"eval_cer": 0.70778065419221,
|
993 |
+
"eval_loss": 2.76908802986145,
|
994 |
+
"eval_runtime": 239.0894,
|
995 |
+
"eval_samples_per_second": 22.841,
|
996 |
+
"eval_steps_per_second": 2.857,
|
997 |
+
"eval_wer": 1.9365166483717526,
|
998 |
+
"step": 8700
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 17.02127659574468,
|
1002 |
+
"eval_cer": 0.7069205406909579,
|
1003 |
+
"eval_loss": 2.731661081314087,
|
1004 |
+
"eval_runtime": 231.1522,
|
1005 |
+
"eval_samples_per_second": 23.625,
|
1006 |
+
"eval_steps_per_second": 2.955,
|
1007 |
+
"eval_wer": 1.9420051225759238,
|
1008 |
+
"step": 8800
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 17.214700193423596,
|
1012 |
+
"eval_cer": 0.7056388029243859,
|
1013 |
+
"eval_loss": 2.683185577392578,
|
1014 |
+
"eval_runtime": 229.2327,
|
1015 |
+
"eval_samples_per_second": 23.823,
|
1016 |
+
"eval_steps_per_second": 2.98,
|
1017 |
+
"eval_wer": 1.9489571899012075,
|
1018 |
+
"step": 8900
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 17.408123791102515,
|
1022 |
+
"grad_norm": 4.358935832977295,
|
1023 |
+
"learning_rate": 2.1585600000000002e-05,
|
1024 |
+
"loss": 2.6749,
|
1025 |
+
"step": 9000
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 17.408123791102515,
|
1029 |
+
"eval_cer": 0.7020128342426364,
|
1030 |
+
"eval_loss": 2.6420364379882812,
|
1031 |
+
"eval_runtime": 229.374,
|
1032 |
+
"eval_samples_per_second": 23.808,
|
1033 |
+
"eval_steps_per_second": 2.978,
|
1034 |
+
"eval_wer": 1.978412001463593,
|
1035 |
+
"step": 9000
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 17.60154738878143,
|
1039 |
+
"eval_cer": 0.6991204917825431,
|
1040 |
+
"eval_loss": 2.601982831954956,
|
1041 |
+
"eval_runtime": 229.7146,
|
1042 |
+
"eval_samples_per_second": 23.773,
|
1043 |
+
"eval_steps_per_second": 2.973,
|
1044 |
+
"eval_wer": 1.9414562751555067,
|
1045 |
+
"step": 9100
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 17.79497098646035,
|
1049 |
+
"eval_cer": 0.6994577911947989,
|
1050 |
+
"eval_loss": 2.5666821002960205,
|
1051 |
+
"eval_runtime": 234.5424,
|
1052 |
+
"eval_samples_per_second": 23.284,
|
1053 |
+
"eval_steps_per_second": 2.912,
|
1054 |
+
"eval_wer": 1.9762166117819246,
|
1055 |
+
"step": 9200
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 17.988394584139265,
|
1059 |
+
"eval_cer": 0.6771285701034666,
|
1060 |
+
"eval_loss": 2.517096757888794,
|
1061 |
+
"eval_runtime": 247.5848,
|
1062 |
+
"eval_samples_per_second": 22.057,
|
1063 |
+
"eval_steps_per_second": 2.759,
|
1064 |
+
"eval_wer": 1.9857299670691548,
|
1065 |
+
"step": 9300
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 18.181818181818183,
|
1069 |
+
"eval_cer": 0.6774658695157224,
|
1070 |
+
"eval_loss": 2.492238759994507,
|
1071 |
+
"eval_runtime": 229.5938,
|
1072 |
+
"eval_samples_per_second": 23.785,
|
1073 |
+
"eval_steps_per_second": 2.975,
|
1074 |
+
"eval_wer": 1.9890230515916576,
|
1075 |
+
"step": 9400
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 18.3752417794971,
|
1079 |
+
"grad_norm": 6.681089878082275,
|
1080 |
+
"learning_rate": 2.27856e-05,
|
1081 |
+
"loss": 2.4473,
|
1082 |
+
"step": 9500
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 18.3752417794971,
|
1086 |
+
"eval_cer": 0.6682575955611397,
|
1087 |
+
"eval_loss": 2.445500373840332,
|
1088 |
+
"eval_runtime": 229.8314,
|
1089 |
+
"eval_samples_per_second": 23.761,
|
1090 |
+
"eval_steps_per_second": 2.972,
|
1091 |
+
"eval_wer": 1.9882912550311014,
|
1092 |
+
"step": 9500
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 18.568665377176014,
|
1096 |
+
"eval_cer": 0.6620681513462463,
|
1097 |
+
"eval_loss": 2.4191782474517822,
|
1098 |
+
"eval_runtime": 230.0128,
|
1099 |
+
"eval_samples_per_second": 23.742,
|
1100 |
+
"eval_steps_per_second": 2.969,
|
1101 |
+
"eval_wer": 1.9815221368459568,
|
1102 |
+
"step": 9600
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 18.762088974854933,
|
1106 |
+
"eval_cer": 0.6523454957879736,
|
1107 |
+
"eval_loss": 2.386597156524658,
|
1108 |
+
"eval_runtime": 240.9084,
|
1109 |
+
"eval_samples_per_second": 22.668,
|
1110 |
+
"eval_steps_per_second": 2.835,
|
1111 |
+
"eval_wer": 1.9904866447127698,
|
1112 |
+
"step": 9700
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 18.95551257253385,
|
1116 |
+
"eval_cer": 0.6539392355108822,
|
1117 |
+
"eval_loss": 2.335400342941284,
|
1118 |
+
"eval_runtime": 233.6249,
|
1119 |
+
"eval_samples_per_second": 23.375,
|
1120 |
+
"eval_steps_per_second": 2.923,
|
1121 |
+
"eval_wer": 1.991401390413465,
|
1122 |
+
"step": 9800
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 19.148936170212767,
|
1126 |
+
"eval_cer": 0.6515612746544789,
|
1127 |
+
"eval_loss": 2.3113534450531006,
|
1128 |
+
"eval_runtime": 252.8489,
|
1129 |
+
"eval_samples_per_second": 21.598,
|
1130 |
+
"eval_steps_per_second": 2.701,
|
1131 |
+
"eval_wer": 1.9924990852542992,
|
1132 |
+
"step": 9900
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 19.342359767891683,
|
1136 |
+
"grad_norm": 8.786458015441895,
|
1137 |
+
"learning_rate": 2.39856e-05,
|
1138 |
+
"loss": 2.2307,
|
1139 |
+
"step": 10000
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 19.342359767891683,
|
1143 |
+
"eval_cer": 0.645447722807343,
|
1144 |
+
"eval_loss": 2.269487142562866,
|
1145 |
+
"eval_runtime": 236.1588,
|
1146 |
+
"eval_samples_per_second": 23.124,
|
1147 |
+
"eval_steps_per_second": 2.892,
|
1148 |
+
"eval_wer": 1.9903036955726308,
|
1149 |
+
"step": 10000
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 19.535783365570598,
|
1153 |
+
"eval_cer": 0.6464258911028847,
|
1154 |
+
"eval_loss": 2.246647834777832,
|
1155 |
+
"eval_runtime": 241.6204,
|
1156 |
+
"eval_samples_per_second": 22.602,
|
1157 |
+
"eval_steps_per_second": 2.827,
|
1158 |
+
"eval_wer": 1.9924990852542992,
|
1159 |
+
"step": 10100
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 19.729206963249517,
|
1163 |
+
"eval_cer": 0.6422939733027515,
|
1164 |
+
"eval_loss": 2.2167210578918457,
|
1165 |
+
"eval_runtime": 230.6902,
|
1166 |
+
"eval_samples_per_second": 23.672,
|
1167 |
+
"eval_steps_per_second": 2.961,
|
1168 |
+
"eval_wer": 1.9928649835345773,
|
1169 |
+
"step": 10200
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 19.922630560928432,
|
1173 |
+
"eval_cer": 0.641256777610065,
|
1174 |
+
"eval_loss": 2.176206588745117,
|
1175 |
+
"eval_runtime": 236.5184,
|
1176 |
+
"eval_samples_per_second": 23.089,
|
1177 |
+
"eval_steps_per_second": 2.888,
|
1178 |
+
"eval_wer": 1.991401390413465,
|
1179 |
+
"step": 10300
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 20.0,
|
1183 |
+
"step": 10340,
|
1184 |
+
"total_flos": 1.4857862206321902e+19,
|
1185 |
+
"train_loss": 15.407913101757057,
|
1186 |
+
"train_runtime": 65838.1292,
|
1187 |
+
"train_samples_per_second": 5.022,
|
1188 |
+
"train_steps_per_second": 0.157
|
1189 |
+
}
|
1190 |
+
],
|
1191 |
+
"logging_steps": 500,
|
1192 |
+
"max_steps": 10340,
|
1193 |
+
"num_input_tokens_seen": 0,
|
1194 |
+
"num_train_epochs": 20,
|
1195 |
+
"save_steps": 400,
|
1196 |
+
"stateful_callbacks": {
|
1197 |
+
"TrainerControl": {
|
1198 |
+
"args": {
|
1199 |
+
"should_epoch_stop": false,
|
1200 |
+
"should_evaluate": false,
|
1201 |
+
"should_log": false,
|
1202 |
+
"should_save": true,
|
1203 |
+
"should_training_stop": true
|
1204 |
+
},
|
1205 |
+
"attributes": {}
|
1206 |
+
}
|
1207 |
+
},
|
1208 |
+
"total_flos": 1.4857862206321902e+19,
|
1209 |
+
"train_batch_size": 16,
|
1210 |
+
"trial_name": null,
|
1211 |
+
"trial_params": null
|
1212 |
+
}
|