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-kana
|
| 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: 0.
|
| 22 |
-
- Wer:
|
| 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-kana
|
| 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: 0.5729
|
| 26 |
+
- Wer: 0.9998
|
| 27 |
+
- Cer: 0.3126
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.962245885769605,
|
| 3 |
+
"eval_cer": 0.3126101450198526,
|
| 4 |
+
"eval_loss": 0.5728740096092224,
|
| 5 |
+
"eval_runtime": 258.7219,
|
| 6 |
+
"eval_samples": 5461,
|
| 7 |
+
"eval_samples_per_second": 21.108,
|
| 8 |
+
"eval_steps_per_second": 2.64,
|
| 9 |
+
"eval_wer": 0.999816883354697,
|
| 10 |
+
"total_flos": 1.4589649587726338e+19,
|
| 11 |
+
"train_loss": 5.084269817855007,
|
| 12 |
+
"train_runtime": 64283.8792,
|
| 13 |
+
"train_samples": 16528,
|
| 14 |
+
"train_samples_per_second": 5.142,
|
| 15 |
+
"train_steps_per_second": 0.161
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.962245885769605,
|
| 3 |
+
"eval_cer": 0.3126101450198526,
|
| 4 |
+
"eval_loss": 0.5728740096092224,
|
| 5 |
+
"eval_runtime": 258.7219,
|
| 6 |
+
"eval_samples": 5461,
|
| 7 |
+
"eval_samples_per_second": 21.108,
|
| 8 |
+
"eval_steps_per_second": 2.64,
|
| 9 |
+
"eval_wer": 0.999816883354697
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.962245885769605,
|
| 3 |
+
"total_flos": 1.4589649587726338e+19,
|
| 4 |
+
"train_loss": 5.084269817855007,
|
| 5 |
+
"train_runtime": 64283.8792,
|
| 6 |
+
"train_samples": 16528,
|
| 7 |
+
"train_samples_per_second": 5.142,
|
| 8 |
+
"train_steps_per_second": 0.161
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5734274387359619,
|
| 3 |
+
"best_model_checkpoint": "./Hubert-common_voice_JSUT-ja-demo-kana/checkpoint-10200",
|
| 4 |
+
"epoch": 19.962245885769605,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 10320,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1936108422071636,
|
| 13 |
+
"eval_cer": 6.16957909562534,
|
| 14 |
+
"eval_loss": 41.956024169921875,
|
| 15 |
+
"eval_runtime": 229.6586,
|
| 16 |
+
"eval_samples_per_second": 23.779,
|
| 17 |
+
"eval_steps_per_second": 2.974,
|
| 18 |
+
"eval_wer": 1.5293902215711408,
|
| 19 |
+
"step": 100
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.3872216844143272,
|
| 23 |
+
"eval_cer": 5.972248763190861,
|
| 24 |
+
"eval_loss": 41.465721130371094,
|
| 25 |
+
"eval_runtime": 227.3403,
|
| 26 |
+
"eval_samples_per_second": 24.021,
|
| 27 |
+
"eval_steps_per_second": 3.004,
|
| 28 |
+
"eval_wer": 1.4235488005859733,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.5808325266214908,
|
| 33 |
+
"eval_cer": 3.732693519049338,
|
| 34 |
+
"eval_loss": 40.27690505981445,
|
| 35 |
+
"eval_runtime": 227.0532,
|
| 36 |
+
"eval_samples_per_second": 24.052,
|
| 37 |
+
"eval_steps_per_second": 3.008,
|
| 38 |
+
"eval_wer": 1.1847646951107855,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.7744433688286544,
|
| 43 |
+
"eval_cer": 0.9962559540239647,
|
| 44 |
+
"eval_loss": 36.3010139465332,
|
| 45 |
+
"eval_runtime": 226.5945,
|
| 46 |
+
"eval_samples_per_second": 24.1,
|
| 47 |
+
"eval_steps_per_second": 3.014,
|
| 48 |
+
"eval_wer": 1.0,
|
| 49 |
+
"step": 400
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.968054211035818,
|
| 53 |
+
"grad_norm": 145.3476104736328,
|
| 54 |
+
"learning_rate": 1.188e-06,
|
| 55 |
+
"loss": 31.4419,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.968054211035818,
|
| 60 |
+
"eval_cer": 0.9991365338202717,
|
| 61 |
+
"eval_loss": 24.542619705200195,
|
| 62 |
+
"eval_runtime": 252.7587,
|
| 63 |
+
"eval_samples_per_second": 21.606,
|
| 64 |
+
"eval_steps_per_second": 2.702,
|
| 65 |
+
"eval_wer": 1.0,
|
| 66 |
+
"step": 500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.1606969990319458,
|
| 70 |
+
"eval_cer": 0.9991365338202717,
|
| 71 |
+
"eval_loss": 18.864185333251953,
|
| 72 |
+
"eval_runtime": 245.7063,
|
| 73 |
+
"eval_samples_per_second": 22.226,
|
| 74 |
+
"eval_steps_per_second": 2.78,
|
| 75 |
+
"eval_wer": 1.0,
|
| 76 |
+
"step": 600
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.3543078412391094,
|
| 80 |
+
"eval_cer": 0.9991365338202717,
|
| 81 |
+
"eval_loss": 17.665119171142578,
|
| 82 |
+
"eval_runtime": 248.5924,
|
| 83 |
+
"eval_samples_per_second": 21.968,
|
| 84 |
+
"eval_steps_per_second": 2.747,
|
| 85 |
+
"eval_wer": 1.0,
|
| 86 |
+
"step": 700
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.547918683446273,
|
| 90 |
+
"eval_cer": 0.9991719217784573,
|
| 91 |
+
"eval_loss": 17.200698852539062,
|
| 92 |
+
"eval_runtime": 253.0263,
|
| 93 |
+
"eval_samples_per_second": 21.583,
|
| 94 |
+
"eval_steps_per_second": 2.699,
|
| 95 |
+
"eval_wer": 1.0,
|
| 96 |
+
"step": 800
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.7415295256534367,
|
| 100 |
+
"eval_cer": 0.9991365338202717,
|
| 101 |
+
"eval_loss": 16.761735916137695,
|
| 102 |
+
"eval_runtime": 259.4018,
|
| 103 |
+
"eval_samples_per_second": 21.052,
|
| 104 |
+
"eval_steps_per_second": 2.633,
|
| 105 |
+
"eval_wer": 1.0,
|
| 106 |
+
"step": 900
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.9351403678606003,
|
| 110 |
+
"grad_norm": 84.73486328125,
|
| 111 |
+
"learning_rate": 2.3880000000000003e-06,
|
| 112 |
+
"loss": 14.8315,
|
| 113 |
+
"step": 1000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.9351403678606003,
|
| 117 |
+
"eval_cer": 0.9991365338202717,
|
| 118 |
+
"eval_loss": 16.289474487304688,
|
| 119 |
+
"eval_runtime": 251.3459,
|
| 120 |
+
"eval_samples_per_second": 21.727,
|
| 121 |
+
"eval_steps_per_second": 2.717,
|
| 122 |
+
"eval_wer": 1.0,
|
| 123 |
+
"step": 1000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.127783155856728,
|
| 127 |
+
"eval_cer": 0.9991365338202717,
|
| 128 |
+
"eval_loss": 15.787718772888184,
|
| 129 |
+
"eval_runtime": 256.1973,
|
| 130 |
+
"eval_samples_per_second": 21.316,
|
| 131 |
+
"eval_steps_per_second": 2.666,
|
| 132 |
+
"eval_wer": 1.0,
|
| 133 |
+
"step": 1100
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.3213939980638916,
|
| 137 |
+
"eval_cer": 0.9991365338202717,
|
| 138 |
+
"eval_loss": 15.248761177062988,
|
| 139 |
+
"eval_runtime": 250.6433,
|
| 140 |
+
"eval_samples_per_second": 21.788,
|
| 141 |
+
"eval_steps_per_second": 2.725,
|
| 142 |
+
"eval_wer": 1.0,
|
| 143 |
+
"step": 1200
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.515004840271055,
|
| 147 |
+
"eval_cer": 0.9991365338202717,
|
| 148 |
+
"eval_loss": 14.66799259185791,
|
| 149 |
+
"eval_runtime": 257.3763,
|
| 150 |
+
"eval_samples_per_second": 21.218,
|
| 151 |
+
"eval_steps_per_second": 2.654,
|
| 152 |
+
"eval_wer": 1.0,
|
| 153 |
+
"step": 1300
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.708615682478219,
|
| 157 |
+
"eval_cer": 0.9991365338202717,
|
| 158 |
+
"eval_loss": 14.063650131225586,
|
| 159 |
+
"eval_runtime": 244.7195,
|
| 160 |
+
"eval_samples_per_second": 22.315,
|
| 161 |
+
"eval_steps_per_second": 2.791,
|
| 162 |
+
"eval_wer": 1.0,
|
| 163 |
+
"step": 1400
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.9022265246853824,
|
| 167 |
+
"grad_norm": 72.20648193359375,
|
| 168 |
+
"learning_rate": 3.588e-06,
|
| 169 |
+
"loss": 12.4363,
|
| 170 |
+
"step": 1500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.9022265246853824,
|
| 174 |
+
"eval_cer": 0.9991365338202717,
|
| 175 |
+
"eval_loss": 13.421667098999023,
|
| 176 |
+
"eval_runtime": 256.8698,
|
| 177 |
+
"eval_samples_per_second": 21.26,
|
| 178 |
+
"eval_steps_per_second": 2.659,
|
| 179 |
+
"eval_wer": 1.0,
|
| 180 |
+
"step": 1500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.09486931268151,
|
| 184 |
+
"eval_cer": 0.9991365338202717,
|
| 185 |
+
"eval_loss": 12.737384796142578,
|
| 186 |
+
"eval_runtime": 223.924,
|
| 187 |
+
"eval_samples_per_second": 24.388,
|
| 188 |
+
"eval_steps_per_second": 3.05,
|
| 189 |
+
"eval_wer": 1.0,
|
| 190 |
+
"step": 1600
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.2884801548886737,
|
| 194 |
+
"eval_cer": 0.9991365338202717,
|
| 195 |
+
"eval_loss": 12.031902313232422,
|
| 196 |
+
"eval_runtime": 222.2009,
|
| 197 |
+
"eval_samples_per_second": 24.577,
|
| 198 |
+
"eval_steps_per_second": 3.074,
|
| 199 |
+
"eval_wer": 1.0,
|
| 200 |
+
"step": 1700
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.4820909970958374,
|
| 204 |
+
"eval_cer": 0.9991365338202717,
|
| 205 |
+
"eval_loss": 11.298233032226562,
|
| 206 |
+
"eval_runtime": 225.5639,
|
| 207 |
+
"eval_samples_per_second": 24.21,
|
| 208 |
+
"eval_steps_per_second": 3.028,
|
| 209 |
+
"eval_wer": 1.0,
|
| 210 |
+
"step": 1800
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.675701839303001,
|
| 214 |
+
"eval_cer": 0.9991719217784573,
|
| 215 |
+
"eval_loss": 10.557957649230957,
|
| 216 |
+
"eval_runtime": 227.931,
|
| 217 |
+
"eval_samples_per_second": 23.959,
|
| 218 |
+
"eval_steps_per_second": 2.997,
|
| 219 |
+
"eval_wer": 1.0,
|
| 220 |
+
"step": 1900
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.8693126815101646,
|
| 224 |
+
"grad_norm": 87.52015686035156,
|
| 225 |
+
"learning_rate": 4.788e-06,
|
| 226 |
+
"loss": 9.8267,
|
| 227 |
+
"step": 2000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.8693126815101646,
|
| 231 |
+
"eval_cer": 0.9991365338202717,
|
| 232 |
+
"eval_loss": 9.812894821166992,
|
| 233 |
+
"eval_runtime": 227.4635,
|
| 234 |
+
"eval_samples_per_second": 24.008,
|
| 235 |
+
"eval_steps_per_second": 3.003,
|
| 236 |
+
"eval_wer": 1.0,
|
| 237 |
+
"step": 2000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.061955469506293,
|
| 241 |
+
"eval_cer": 0.9991365338202717,
|
| 242 |
+
"eval_loss": 9.064043998718262,
|
| 243 |
+
"eval_runtime": 223.8694,
|
| 244 |
+
"eval_samples_per_second": 24.394,
|
| 245 |
+
"eval_steps_per_second": 3.051,
|
| 246 |
+
"eval_wer": 1.0,
|
| 247 |
+
"step": 2100
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 4.255566311713456,
|
| 251 |
+
"eval_cer": 0.9991719217784573,
|
| 252 |
+
"eval_loss": 8.337604522705078,
|
| 253 |
+
"eval_runtime": 224.9536,
|
| 254 |
+
"eval_samples_per_second": 24.276,
|
| 255 |
+
"eval_steps_per_second": 3.036,
|
| 256 |
+
"eval_wer": 1.0,
|
| 257 |
+
"step": 2200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 4.44917715392062,
|
| 261 |
+
"eval_cer": 0.9991365338202717,
|
| 262 |
+
"eval_loss": 7.628673076629639,
|
| 263 |
+
"eval_runtime": 228.2923,
|
| 264 |
+
"eval_samples_per_second": 23.921,
|
| 265 |
+
"eval_steps_per_second": 2.992,
|
| 266 |
+
"eval_wer": 1.0,
|
| 267 |
+
"step": 2300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.642787996127783,
|
| 271 |
+
"eval_cer": 0.9991365338202717,
|
| 272 |
+
"eval_loss": 6.967807769775391,
|
| 273 |
+
"eval_runtime": 228.5115,
|
| 274 |
+
"eval_samples_per_second": 23.898,
|
| 275 |
+
"eval_steps_per_second": 2.989,
|
| 276 |
+
"eval_wer": 1.0,
|
| 277 |
+
"step": 2400
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.836398838334947,
|
| 281 |
+
"grad_norm": 34.805992126464844,
|
| 282 |
+
"learning_rate": 5.988e-06,
|
| 283 |
+
"loss": 6.9778,
|
| 284 |
+
"step": 2500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.836398838334947,
|
| 288 |
+
"eval_cer": 0.9991719217784573,
|
| 289 |
+
"eval_loss": 6.363549709320068,
|
| 290 |
+
"eval_runtime": 227.6007,
|
| 291 |
+
"eval_samples_per_second": 23.994,
|
| 292 |
+
"eval_steps_per_second": 3.001,
|
| 293 |
+
"eval_wer": 1.0,
|
| 294 |
+
"step": 2500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.029041626331074,
|
| 298 |
+
"eval_cer": 0.9991365338202717,
|
| 299 |
+
"eval_loss": 5.8258442878723145,
|
| 300 |
+
"eval_runtime": 265.7388,
|
| 301 |
+
"eval_samples_per_second": 20.55,
|
| 302 |
+
"eval_steps_per_second": 2.57,
|
| 303 |
+
"eval_wer": 1.0,
|
| 304 |
+
"step": 2600
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.2226524685382385,
|
| 308 |
+
"eval_cer": 0.9991365338202717,
|
| 309 |
+
"eval_loss": 5.367654800415039,
|
| 310 |
+
"eval_runtime": 226.9427,
|
| 311 |
+
"eval_samples_per_second": 24.063,
|
| 312 |
+
"eval_steps_per_second": 3.01,
|
| 313 |
+
"eval_wer": 1.0,
|
| 314 |
+
"step": 2700
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.416263310745402,
|
| 318 |
+
"eval_cer": 0.9991365338202717,
|
| 319 |
+
"eval_loss": 4.988757133483887,
|
| 320 |
+
"eval_runtime": 227.6207,
|
| 321 |
+
"eval_samples_per_second": 23.992,
|
| 322 |
+
"eval_steps_per_second": 3.001,
|
| 323 |
+
"eval_wer": 1.0,
|
| 324 |
+
"step": 2800
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.609874152952566,
|
| 328 |
+
"eval_cer": 0.9991365338202717,
|
| 329 |
+
"eval_loss": 4.695638656616211,
|
| 330 |
+
"eval_runtime": 230.3237,
|
| 331 |
+
"eval_samples_per_second": 23.71,
|
| 332 |
+
"eval_steps_per_second": 2.965,
|
| 333 |
+
"eval_wer": 1.0,
|
| 334 |
+
"step": 2900
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 5.803484995159729,
|
| 338 |
+
"grad_norm": 3.1527926921844482,
|
| 339 |
+
"learning_rate": 7.1880000000000005e-06,
|
| 340 |
+
"loss": 4.8731,
|
| 341 |
+
"step": 3000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 5.803484995159729,
|
| 345 |
+
"eval_cer": 0.9991365338202717,
|
| 346 |
+
"eval_loss": 4.478826999664307,
|
| 347 |
+
"eval_runtime": 234.3555,
|
| 348 |
+
"eval_samples_per_second": 23.302,
|
| 349 |
+
"eval_steps_per_second": 2.914,
|
| 350 |
+
"eval_wer": 1.0,
|
| 351 |
+
"step": 3000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.997095837366892,
|
| 355 |
+
"eval_cer": 0.9991365338202717,
|
| 356 |
+
"eval_loss": 4.328735828399658,
|
| 357 |
+
"eval_runtime": 226.0428,
|
| 358 |
+
"eval_samples_per_second": 24.159,
|
| 359 |
+
"eval_steps_per_second": 3.022,
|
| 360 |
+
"eval_wer": 1.0,
|
| 361 |
+
"step": 3100
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 6.18973862536302,
|
| 365 |
+
"eval_cer": 0.9991365338202717,
|
| 366 |
+
"eval_loss": 4.20569372177124,
|
| 367 |
+
"eval_runtime": 227.3968,
|
| 368 |
+
"eval_samples_per_second": 24.015,
|
| 369 |
+
"eval_steps_per_second": 3.004,
|
| 370 |
+
"eval_wer": 1.0,
|
| 371 |
+
"step": 3200
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 6.383349467570184,
|
| 375 |
+
"eval_cer": 0.9991365338202717,
|
| 376 |
+
"eval_loss": 4.1447553634643555,
|
| 377 |
+
"eval_runtime": 226.8138,
|
| 378 |
+
"eval_samples_per_second": 24.077,
|
| 379 |
+
"eval_steps_per_second": 3.011,
|
| 380 |
+
"eval_wer": 1.0,
|
| 381 |
+
"step": 3300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 6.5769603097773475,
|
| 385 |
+
"eval_cer": 0.9991365338202717,
|
| 386 |
+
"eval_loss": 4.109466552734375,
|
| 387 |
+
"eval_runtime": 223.6971,
|
| 388 |
+
"eval_samples_per_second": 24.412,
|
| 389 |
+
"eval_steps_per_second": 3.053,
|
| 390 |
+
"eval_wer": 1.0,
|
| 391 |
+
"step": 3400
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 6.770571151984511,
|
| 395 |
+
"grad_norm": 1.822492241859436,
|
| 396 |
+
"learning_rate": 8.388e-06,
|
| 397 |
+
"loss": 4.1216,
|
| 398 |
+
"step": 3500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.770571151984511,
|
| 402 |
+
"eval_cer": 0.9991365338202717,
|
| 403 |
+
"eval_loss": 4.085766792297363,
|
| 404 |
+
"eval_runtime": 228.1097,
|
| 405 |
+
"eval_samples_per_second": 23.94,
|
| 406 |
+
"eval_steps_per_second": 2.994,
|
| 407 |
+
"eval_wer": 1.0,
|
| 408 |
+
"step": 3500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 6.964181994191675,
|
| 412 |
+
"eval_cer": 0.9991365338202717,
|
| 413 |
+
"eval_loss": 4.072465896606445,
|
| 414 |
+
"eval_runtime": 276.0608,
|
| 415 |
+
"eval_samples_per_second": 19.782,
|
| 416 |
+
"eval_steps_per_second": 2.474,
|
| 417 |
+
"eval_wer": 1.0,
|
| 418 |
+
"step": 3600
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 7.156824782187803,
|
| 422 |
+
"eval_cer": 0.9991365338202717,
|
| 423 |
+
"eval_loss": 4.064761161804199,
|
| 424 |
+
"eval_runtime": 223.6339,
|
| 425 |
+
"eval_samples_per_second": 24.419,
|
| 426 |
+
"eval_steps_per_second": 3.054,
|
| 427 |
+
"eval_wer": 1.0,
|
| 428 |
+
"step": 3700
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.350435624394966,
|
| 432 |
+
"eval_cer": 0.9991365338202717,
|
| 433 |
+
"eval_loss": 4.057798385620117,
|
| 434 |
+
"eval_runtime": 223.5104,
|
| 435 |
+
"eval_samples_per_second": 24.433,
|
| 436 |
+
"eval_steps_per_second": 3.056,
|
| 437 |
+
"eval_wer": 1.0,
|
| 438 |
+
"step": 3800
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 7.54404646660213,
|
| 442 |
+
"eval_cer": 0.9991365338202717,
|
| 443 |
+
"eval_loss": 4.0493927001953125,
|
| 444 |
+
"eval_runtime": 227.6334,
|
| 445 |
+
"eval_samples_per_second": 23.99,
|
| 446 |
+
"eval_steps_per_second": 3.0,
|
| 447 |
+
"eval_wer": 1.0,
|
| 448 |
+
"step": 3900
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 7.737657308809293,
|
| 452 |
+
"grad_norm": 0.8575032949447632,
|
| 453 |
+
"learning_rate": 9.588e-06,
|
| 454 |
+
"loss": 4.0264,
|
| 455 |
+
"step": 4000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 7.737657308809293,
|
| 459 |
+
"eval_cer": 0.9991365338202717,
|
| 460 |
+
"eval_loss": 4.036725044250488,
|
| 461 |
+
"eval_runtime": 232.0149,
|
| 462 |
+
"eval_samples_per_second": 23.537,
|
| 463 |
+
"eval_steps_per_second": 2.944,
|
| 464 |
+
"eval_wer": 1.0,
|
| 465 |
+
"step": 4000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.931268151016457,
|
| 469 |
+
"eval_cer": 0.9991365338202717,
|
| 470 |
+
"eval_loss": 4.027583122253418,
|
| 471 |
+
"eval_runtime": 228.3311,
|
| 472 |
+
"eval_samples_per_second": 23.917,
|
| 473 |
+
"eval_steps_per_second": 2.991,
|
| 474 |
+
"eval_wer": 1.0,
|
| 475 |
+
"step": 4100
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 8.123910939012585,
|
| 479 |
+
"eval_cer": 0.9991365338202717,
|
| 480 |
+
"eval_loss": 4.012051582336426,
|
| 481 |
+
"eval_runtime": 230.306,
|
| 482 |
+
"eval_samples_per_second": 23.712,
|
| 483 |
+
"eval_steps_per_second": 2.966,
|
| 484 |
+
"eval_wer": 1.0,
|
| 485 |
+
"step": 4200
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 8.317521781219748,
|
| 489 |
+
"eval_cer": 0.9991365338202717,
|
| 490 |
+
"eval_loss": 3.9720146656036377,
|
| 491 |
+
"eval_runtime": 232.5487,
|
| 492 |
+
"eval_samples_per_second": 23.483,
|
| 493 |
+
"eval_steps_per_second": 2.937,
|
| 494 |
+
"eval_wer": 1.0,
|
| 495 |
+
"step": 4300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.511132623426912,
|
| 499 |
+
"eval_cer": 0.9991365338202717,
|
| 500 |
+
"eval_loss": 3.903093099594116,
|
| 501 |
+
"eval_runtime": 225.8081,
|
| 502 |
+
"eval_samples_per_second": 24.184,
|
| 503 |
+
"eval_steps_per_second": 3.025,
|
| 504 |
+
"eval_wer": 1.0,
|
| 505 |
+
"step": 4400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 8.704743465634076,
|
| 509 |
+
"grad_norm": 1.4530484676361084,
|
| 510 |
+
"learning_rate": 1.0787999999999999e-05,
|
| 511 |
+
"loss": 3.937,
|
| 512 |
+
"step": 4500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.704743465634076,
|
| 516 |
+
"eval_cer": 0.9991365338202717,
|
| 517 |
+
"eval_loss": 3.8090686798095703,
|
| 518 |
+
"eval_runtime": 230.0214,
|
| 519 |
+
"eval_samples_per_second": 23.741,
|
| 520 |
+
"eval_steps_per_second": 2.969,
|
| 521 |
+
"eval_wer": 1.0,
|
| 522 |
+
"step": 4500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 8.89835430784124,
|
| 526 |
+
"eval_cer": 0.9991365338202717,
|
| 527 |
+
"eval_loss": 3.6690022945404053,
|
| 528 |
+
"eval_runtime": 229.4694,
|
| 529 |
+
"eval_samples_per_second": 23.798,
|
| 530 |
+
"eval_steps_per_second": 2.976,
|
| 531 |
+
"eval_wer": 1.0,
|
| 532 |
+
"step": 4600
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 9.090997095837366,
|
| 536 |
+
"eval_cer": 0.9991365338202717,
|
| 537 |
+
"eval_loss": 3.475857973098755,
|
| 538 |
+
"eval_runtime": 229.5875,
|
| 539 |
+
"eval_samples_per_second": 23.786,
|
| 540 |
+
"eval_steps_per_second": 2.975,
|
| 541 |
+
"eval_wer": 1.0,
|
| 542 |
+
"step": 4700
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 9.28460793804453,
|
| 546 |
+
"eval_cer": 0.998676490363859,
|
| 547 |
+
"eval_loss": 3.2108352184295654,
|
| 548 |
+
"eval_runtime": 224.0108,
|
| 549 |
+
"eval_samples_per_second": 24.378,
|
| 550 |
+
"eval_steps_per_second": 3.049,
|
| 551 |
+
"eval_wer": 1.0,
|
| 552 |
+
"step": 4800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 9.478218780251694,
|
| 556 |
+
"eval_cer": 0.6453277278807568,
|
| 557 |
+
"eval_loss": 2.681295394897461,
|
| 558 |
+
"eval_runtime": 226.867,
|
| 559 |
+
"eval_samples_per_second": 24.071,
|
| 560 |
+
"eval_steps_per_second": 3.011,
|
| 561 |
+
"eval_wer": 1.0,
|
| 562 |
+
"step": 4900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 9.671829622458858,
|
| 566 |
+
"grad_norm": 13.226855278015137,
|
| 567 |
+
"learning_rate": 1.1988000000000001e-05,
|
| 568 |
+
"loss": 3.1866,
|
| 569 |
+
"step": 5000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 9.671829622458858,
|
| 573 |
+
"eval_cer": 0.5372387483986949,
|
| 574 |
+
"eval_loss": 2.3876163959503174,
|
| 575 |
+
"eval_runtime": 226.669,
|
| 576 |
+
"eval_samples_per_second": 24.092,
|
| 577 |
+
"eval_steps_per_second": 3.013,
|
| 578 |
+
"eval_wer": 1.000183116645303,
|
| 579 |
+
"step": 5000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.86544046466602,
|
| 583 |
+
"eval_cer": 0.4901869191951363,
|
| 584 |
+
"eval_loss": 2.16782808303833,
|
| 585 |
+
"eval_runtime": 225.6765,
|
| 586 |
+
"eval_samples_per_second": 24.198,
|
| 587 |
+
"eval_steps_per_second": 3.026,
|
| 588 |
+
"eval_wer": 1.0,
|
| 589 |
+
"step": 5100
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 10.058083252662149,
|
| 593 |
+
"eval_cer": 0.4530012527337198,
|
| 594 |
+
"eval_loss": 1.9945032596588135,
|
| 595 |
+
"eval_runtime": 231.2758,
|
| 596 |
+
"eval_samples_per_second": 23.612,
|
| 597 |
+
"eval_steps_per_second": 2.953,
|
| 598 |
+
"eval_wer": 1.000183116645303,
|
| 599 |
+
"step": 5200
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 10.251694094869313,
|
| 603 |
+
"eval_cer": 0.4269698706924008,
|
| 604 |
+
"eval_loss": 1.8575785160064697,
|
| 605 |
+
"eval_runtime": 226.1334,
|
| 606 |
+
"eval_samples_per_second": 24.149,
|
| 607 |
+
"eval_steps_per_second": 3.02,
|
| 608 |
+
"eval_wer": 1.0,
|
| 609 |
+
"step": 5300
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.445304937076477,
|
| 613 |
+
"eval_cer": 0.43989355302177774,
|
| 614 |
+
"eval_loss": 1.7787507772445679,
|
| 615 |
+
"eval_runtime": 226.9349,
|
| 616 |
+
"eval_samples_per_second": 24.064,
|
| 617 |
+
"eval_steps_per_second": 3.01,
|
| 618 |
+
"eval_wer": 1.0,
|
| 619 |
+
"step": 5400
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 10.63891577928364,
|
| 623 |
+
"grad_norm": 8.360028266906738,
|
| 624 |
+
"learning_rate": 1.3188e-05,
|
| 625 |
+
"loss": 1.9458,
|
| 626 |
+
"step": 5500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 10.63891577928364,
|
| 630 |
+
"eval_cer": 0.40938205547416323,
|
| 631 |
+
"eval_loss": 1.6519718170166016,
|
| 632 |
+
"eval_runtime": 227.1281,
|
| 633 |
+
"eval_samples_per_second": 24.044,
|
| 634 |
+
"eval_steps_per_second": 3.007,
|
| 635 |
+
"eval_wer": 1.0,
|
| 636 |
+
"step": 5500
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 10.832526621490803,
|
| 640 |
+
"eval_cer": 0.38743444380746117,
|
| 641 |
+
"eval_loss": 1.5545194149017334,
|
| 642 |
+
"eval_runtime": 225.52,
|
| 643 |
+
"eval_samples_per_second": 24.215,
|
| 644 |
+
"eval_steps_per_second": 3.029,
|
| 645 |
+
"eval_wer": 1.0,
|
| 646 |
+
"step": 5600
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 11.025169409486931,
|
| 650 |
+
"eval_cer": 0.3800312829550361,
|
| 651 |
+
"eval_loss": 1.4698398113250732,
|
| 652 |
+
"eval_runtime": 230.154,
|
| 653 |
+
"eval_samples_per_second": 23.728,
|
| 654 |
+
"eval_steps_per_second": 2.968,
|
| 655 |
+
"eval_wer": 1.0,
|
| 656 |
+
"step": 5700
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 11.218780251694096,
|
| 660 |
+
"eval_cer": 0.3777310656729728,
|
| 661 |
+
"eval_loss": 1.4052294492721558,
|
| 662 |
+
"eval_runtime": 229.123,
|
| 663 |
+
"eval_samples_per_second": 23.834,
|
| 664 |
+
"eval_steps_per_second": 2.981,
|
| 665 |
+
"eval_wer": 1.0,
|
| 666 |
+
"step": 5800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 11.412391093901258,
|
| 670 |
+
"eval_cer": 0.3658124013560666,
|
| 671 |
+
"eval_loss": 1.3275731801986694,
|
| 672 |
+
"eval_runtime": 230.2917,
|
| 673 |
+
"eval_samples_per_second": 23.713,
|
| 674 |
+
"eval_steps_per_second": 2.966,
|
| 675 |
+
"eval_wer": 1.0,
|
| 676 |
+
"step": 5900
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 11.606001936108422,
|
| 680 |
+
"grad_norm": 4.284916877746582,
|
| 681 |
+
"learning_rate": 1.4388000000000002e-05,
|
| 682 |
+
"loss": 1.4263,
|
| 683 |
+
"step": 6000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 11.606001936108422,
|
| 687 |
+
"eval_cer": 0.36683865214344863,
|
| 688 |
+
"eval_loss": 1.2710145711898804,
|
| 689 |
+
"eval_runtime": 237.3574,
|
| 690 |
+
"eval_samples_per_second": 23.008,
|
| 691 |
+
"eval_steps_per_second": 2.878,
|
| 692 |
+
"eval_wer": 1.0,
|
| 693 |
+
"step": 6000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.799612778315586,
|
| 697 |
+
"eval_cer": 0.35358940059876426,
|
| 698 |
+
"eval_loss": 1.2150152921676636,
|
| 699 |
+
"eval_runtime": 229.8802,
|
| 700 |
+
"eval_samples_per_second": 23.756,
|
| 701 |
+
"eval_steps_per_second": 2.971,
|
| 702 |
+
"eval_wer": 1.0,
|
| 703 |
+
"step": 6100
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 11.99322362052275,
|
| 707 |
+
"eval_cer": 0.3531364347339887,
|
| 708 |
+
"eval_loss": 1.1585793495178223,
|
| 709 |
+
"eval_runtime": 229.1811,
|
| 710 |
+
"eval_samples_per_second": 23.828,
|
| 711 |
+
"eval_steps_per_second": 2.98,
|
| 712 |
+
"eval_wer": 1.0,
|
| 713 |
+
"step": 6200
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 12.185866408518876,
|
| 717 |
+
"eval_cer": 0.3518553906476704,
|
| 718 |
+
"eval_loss": 1.1155860424041748,
|
| 719 |
+
"eval_runtime": 229.1686,
|
| 720 |
+
"eval_samples_per_second": 23.83,
|
| 721 |
+
"eval_steps_per_second": 2.98,
|
| 722 |
+
"eval_wer": 1.0,
|
| 723 |
+
"step": 6300
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.37947725072604,
|
| 727 |
+
"eval_cer": 0.34836613797057137,
|
| 728 |
+
"eval_loss": 1.0729304552078247,
|
| 729 |
+
"eval_runtime": 235.2642,
|
| 730 |
+
"eval_samples_per_second": 23.212,
|
| 731 |
+
"eval_steps_per_second": 2.903,
|
| 732 |
+
"eval_wer": 1.0,
|
| 733 |
+
"step": 6400
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 12.573088092933205,
|
| 737 |
+
"grad_norm": 7.104965686798096,
|
| 738 |
+
"learning_rate": 1.5588e-05,
|
| 739 |
+
"loss": 1.1212,
|
| 740 |
+
"step": 6500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 12.573088092933205,
|
| 744 |
+
"eval_cer": 0.3466533607943889,
|
| 745 |
+
"eval_loss": 1.0344808101654053,
|
| 746 |
+
"eval_runtime": 229.0405,
|
| 747 |
+
"eval_samples_per_second": 23.843,
|
| 748 |
+
"eval_steps_per_second": 2.982,
|
| 749 |
+
"eval_wer": 1.0,
|
| 750 |
+
"step": 6500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 12.766698935140369,
|
| 754 |
+
"eval_cer": 0.3428314613103453,
|
| 755 |
+
"eval_loss": 0.988746166229248,
|
| 756 |
+
"eval_runtime": 228.7064,
|
| 757 |
+
"eval_samples_per_second": 23.878,
|
| 758 |
+
"eval_steps_per_second": 2.986,
|
| 759 |
+
"eval_wer": 1.0,
|
| 760 |
+
"step": 6600
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 12.96030977734753,
|
| 764 |
+
"eval_cer": 0.3416636586902209,
|
| 765 |
+
"eval_loss": 0.963031530380249,
|
| 766 |
+
"eval_runtime": 229.2204,
|
| 767 |
+
"eval_samples_per_second": 23.824,
|
| 768 |
+
"eval_steps_per_second": 2.98,
|
| 769 |
+
"eval_wer": 1.0,
|
| 770 |
+
"step": 6700
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 13.152952565343659,
|
| 774 |
+
"eval_cer": 0.3380753197302022,
|
| 775 |
+
"eval_loss": 0.9259727597236633,
|
| 776 |
+
"eval_runtime": 230.8473,
|
| 777 |
+
"eval_samples_per_second": 23.656,
|
| 778 |
+
"eval_steps_per_second": 2.959,
|
| 779 |
+
"eval_wer": 1.0,
|
| 780 |
+
"step": 6800
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 13.346563407550823,
|
| 784 |
+
"eval_cer": 0.3397102433983764,
|
| 785 |
+
"eval_loss": 0.9005178809165955,
|
| 786 |
+
"eval_runtime": 229.79,
|
| 787 |
+
"eval_samples_per_second": 23.765,
|
| 788 |
+
"eval_steps_per_second": 2.972,
|
| 789 |
+
"eval_wer": 1.0,
|
| 790 |
+
"step": 6900
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 13.540174249757987,
|
| 794 |
+
"grad_norm": 8.212745666503906,
|
| 795 |
+
"learning_rate": 1.6788e-05,
|
| 796 |
+
"loss": 0.9141,
|
| 797 |
+
"step": 7000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 13.540174249757987,
|
| 801 |
+
"eval_cer": 0.33693582747662626,
|
| 802 |
+
"eval_loss": 0.8763672709465027,
|
| 803 |
+
"eval_runtime": 233.0771,
|
| 804 |
+
"eval_samples_per_second": 23.43,
|
| 805 |
+
"eval_steps_per_second": 2.93,
|
| 806 |
+
"eval_wer": 1.0,
|
| 807 |
+
"step": 7000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.73378509196515,
|
| 811 |
+
"eval_cer": 0.3362776114543743,
|
| 812 |
+
"eval_loss": 0.8511508703231812,
|
| 813 |
+
"eval_runtime": 228.4896,
|
| 814 |
+
"eval_samples_per_second": 23.9,
|
| 815 |
+
"eval_steps_per_second": 2.989,
|
| 816 |
+
"eval_wer": 1.0,
|
| 817 |
+
"step": 7100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 13.927395934172313,
|
| 821 |
+
"eval_cer": 0.3351098088342499,
|
| 822 |
+
"eval_loss": 0.8273207545280457,
|
| 823 |
+
"eval_runtime": 228.9007,
|
| 824 |
+
"eval_samples_per_second": 23.858,
|
| 825 |
+
"eval_steps_per_second": 2.984,
|
| 826 |
+
"eval_wer": 1.0,
|
| 827 |
+
"step": 7200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 14.120038722168442,
|
| 831 |
+
"eval_cer": 0.3328520571020093,
|
| 832 |
+
"eval_loss": 0.8083305358886719,
|
| 833 |
+
"eval_runtime": 230.4678,
|
| 834 |
+
"eval_samples_per_second": 23.695,
|
| 835 |
+
"eval_steps_per_second": 2.964,
|
| 836 |
+
"eval_wer": 1.0,
|
| 837 |
+
"step": 7300
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.313649564375606,
|
| 841 |
+
"eval_cer": 0.33002102044716225,
|
| 842 |
+
"eval_loss": 0.7850707769393921,
|
| 843 |
+
"eval_runtime": 234.2407,
|
| 844 |
+
"eval_samples_per_second": 23.314,
|
| 845 |
+
"eval_steps_per_second": 2.916,
|
| 846 |
+
"eval_wer": 0.999816883354697,
|
| 847 |
+
"step": 7400
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 14.507260406582768,
|
| 851 |
+
"grad_norm": 5.25850772857666,
|
| 852 |
+
"learning_rate": 1.7988e-05,
|
| 853 |
+
"loss": 0.7811,
|
| 854 |
+
"step": 7500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 14.507260406582768,
|
| 858 |
+
"eval_cer": 0.3312312886171094,
|
| 859 |
+
"eval_loss": 0.7742574214935303,
|
| 860 |
+
"eval_runtime": 228.7569,
|
| 861 |
+
"eval_samples_per_second": 23.873,
|
| 862 |
+
"eval_steps_per_second": 2.986,
|
| 863 |
+
"eval_wer": 1.0,
|
| 864 |
+
"step": 7500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 14.700871248789932,
|
| 868 |
+
"eval_cer": 0.3272112165672265,
|
| 869 |
+
"eval_loss": 0.7509779334068298,
|
| 870 |
+
"eval_runtime": 225.7839,
|
| 871 |
+
"eval_samples_per_second": 24.187,
|
| 872 |
+
"eval_steps_per_second": 3.025,
|
| 873 |
+
"eval_wer": 0.999816883354697,
|
| 874 |
+
"step": 7600
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 14.894482090997096,
|
| 878 |
+
"eval_cer": 0.3267299403359025,
|
| 879 |
+
"eval_loss": 0.7366129159927368,
|
| 880 |
+
"eval_runtime": 234.848,
|
| 881 |
+
"eval_samples_per_second": 23.253,
|
| 882 |
+
"eval_steps_per_second": 2.908,
|
| 883 |
+
"eval_wer": 1.0,
|
| 884 |
+
"step": 7700
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 15.087124878993224,
|
| 888 |
+
"eval_cer": 0.3253427323750274,
|
| 889 |
+
"eval_loss": 0.7289799451828003,
|
| 890 |
+
"eval_runtime": 233.7629,
|
| 891 |
+
"eval_samples_per_second": 23.361,
|
| 892 |
+
"eval_steps_per_second": 2.922,
|
| 893 |
+
"eval_wer": 1.0,
|
| 894 |
+
"step": 7800
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 15.280735721200386,
|
| 898 |
+
"eval_cer": 0.3247199043109611,
|
| 899 |
+
"eval_loss": 0.7132401466369629,
|
| 900 |
+
"eval_runtime": 240.827,
|
| 901 |
+
"eval_samples_per_second": 22.676,
|
| 902 |
+
"eval_steps_per_second": 2.836,
|
| 903 |
+
"eval_wer": 1.0,
|
| 904 |
+
"step": 7900
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 15.47434656340755,
|
| 908 |
+
"grad_norm": 13.825493812561035,
|
| 909 |
+
"learning_rate": 1.9188e-05,
|
| 910 |
+
"loss": 0.6725,
|
| 911 |
+
"step": 8000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 15.47434656340755,
|
| 915 |
+
"eval_cer": 0.3276924927985505,
|
| 916 |
+
"eval_loss": 0.7190116047859192,
|
| 917 |
+
"eval_runtime": 231.4321,
|
| 918 |
+
"eval_samples_per_second": 23.597,
|
| 919 |
+
"eval_steps_per_second": 2.951,
|
| 920 |
+
"eval_wer": 1.0,
|
| 921 |
+
"step": 8000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.667957405614715,
|
| 925 |
+
"eval_cer": 0.3241253866134432,
|
| 926 |
+
"eval_loss": 0.7005703449249268,
|
| 927 |
+
"eval_runtime": 229.0636,
|
| 928 |
+
"eval_samples_per_second": 23.841,
|
| 929 |
+
"eval_steps_per_second": 2.982,
|
| 930 |
+
"eval_wer": 1.0,
|
| 931 |
+
"step": 8100
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 15.861568247821879,
|
| 935 |
+
"eval_cer": 0.322554161270003,
|
| 936 |
+
"eval_loss": 0.683487594127655,
|
| 937 |
+
"eval_runtime": 230.5943,
|
| 938 |
+
"eval_samples_per_second": 23.682,
|
| 939 |
+
"eval_steps_per_second": 2.962,
|
| 940 |
+
"eval_wer": 1.0,
|
| 941 |
+
"step": 8200
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 16.054211035818007,
|
| 945 |
+
"eval_cer": 0.32088384964364325,
|
| 946 |
+
"eval_loss": 0.6697654724121094,
|
| 947 |
+
"eval_runtime": 253.1459,
|
| 948 |
+
"eval_samples_per_second": 21.573,
|
| 949 |
+
"eval_steps_per_second": 2.698,
|
| 950 |
+
"eval_wer": 0.999816883354697,
|
| 951 |
+
"step": 8300
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 16.24782187802517,
|
| 955 |
+
"eval_cer": 0.3213722034666044,
|
| 956 |
+
"eval_loss": 0.6627610921859741,
|
| 957 |
+
"eval_runtime": 228.1606,
|
| 958 |
+
"eval_samples_per_second": 23.935,
|
| 959 |
+
"eval_steps_per_second": 2.994,
|
| 960 |
+
"eval_wer": 0.999816883354697,
|
| 961 |
+
"step": 8400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 16.44143272023233,
|
| 965 |
+
"grad_norm": 4.491298675537109,
|
| 966 |
+
"learning_rate": 2.0388e-05,
|
| 967 |
+
"loss": 0.606,
|
| 968 |
+
"step": 8500
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 16.44143272023233,
|
| 972 |
+
"eval_cer": 0.320508737286876,
|
| 973 |
+
"eval_loss": 0.6538371443748474,
|
| 974 |
+
"eval_runtime": 229.6742,
|
| 975 |
+
"eval_samples_per_second": 23.777,
|
| 976 |
+
"eval_steps_per_second": 2.974,
|
| 977 |
+
"eval_wer": 1.0,
|
| 978 |
+
"step": 8500
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 16.635043562439495,
|
| 982 |
+
"eval_cer": 0.3186119427281285,
|
| 983 |
+
"eval_loss": 0.652263343334198,
|
| 984 |
+
"eval_runtime": 229.4944,
|
| 985 |
+
"eval_samples_per_second": 23.796,
|
| 986 |
+
"eval_steps_per_second": 2.976,
|
| 987 |
+
"eval_wer": 1.0,
|
| 988 |
+
"step": 8600
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 16.82865440464666,
|
| 992 |
+
"eval_cer": 0.3183005286960953,
|
| 993 |
+
"eval_loss": 0.6448878049850464,
|
| 994 |
+
"eval_runtime": 253.2088,
|
| 995 |
+
"eval_samples_per_second": 21.567,
|
| 996 |
+
"eval_steps_per_second": 2.697,
|
| 997 |
+
"eval_wer": 1.0,
|
| 998 |
+
"step": 8700
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 17.021297192642788,
|
| 1002 |
+
"eval_cer": 0.3179466491142394,
|
| 1003 |
+
"eval_loss": 0.6400793194770813,
|
| 1004 |
+
"eval_runtime": 227.3314,
|
| 1005 |
+
"eval_samples_per_second": 24.022,
|
| 1006 |
+
"eval_steps_per_second": 3.004,
|
| 1007 |
+
"eval_wer": 1.0,
|
| 1008 |
+
"step": 8800
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 17.21490803484995,
|
| 1012 |
+
"eval_cer": 0.3199849955057293,
|
| 1013 |
+
"eval_loss": 0.6333277821540833,
|
| 1014 |
+
"eval_runtime": 227.9774,
|
| 1015 |
+
"eval_samples_per_second": 23.954,
|
| 1016 |
+
"eval_steps_per_second": 2.996,
|
| 1017 |
+
"eval_wer": 1.0,
|
| 1018 |
+
"step": 8900
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 17.408518877057116,
|
| 1022 |
+
"grad_norm": 3.5857622623443604,
|
| 1023 |
+
"learning_rate": 2.1588e-05,
|
| 1024 |
+
"loss": 0.5492,
|
| 1025 |
+
"step": 9000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 17.408518877057116,
|
| 1029 |
+
"eval_cer": 0.320147780113383,
|
| 1030 |
+
"eval_loss": 0.6332593560218811,
|
| 1031 |
+
"eval_runtime": 229.5302,
|
| 1032 |
+
"eval_samples_per_second": 23.792,
|
| 1033 |
+
"eval_steps_per_second": 2.976,
|
| 1034 |
+
"eval_wer": 1.0,
|
| 1035 |
+
"step": 9000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.60212971926428,
|
| 1039 |
+
"eval_cer": 0.3179324939309652,
|
| 1040 |
+
"eval_loss": 0.6219143867492676,
|
| 1041 |
+
"eval_runtime": 227.7602,
|
| 1042 |
+
"eval_samples_per_second": 23.977,
|
| 1043 |
+
"eval_steps_per_second": 2.999,
|
| 1044 |
+
"eval_wer": 1.0,
|
| 1045 |
+
"step": 9100
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 17.795740561471444,
|
| 1049 |
+
"eval_cer": 0.32011239215519743,
|
| 1050 |
+
"eval_loss": 0.6189157366752625,
|
| 1051 |
+
"eval_runtime": 234.0727,
|
| 1052 |
+
"eval_samples_per_second": 23.33,
|
| 1053 |
+
"eval_steps_per_second": 2.918,
|
| 1054 |
+
"eval_wer": 1.0,
|
| 1055 |
+
"step": 9200
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 17.989351403678604,
|
| 1059 |
+
"eval_cer": 0.3165523635617272,
|
| 1060 |
+
"eval_loss": 0.6023225784301758,
|
| 1061 |
+
"eval_runtime": 252.0388,
|
| 1062 |
+
"eval_samples_per_second": 21.667,
|
| 1063 |
+
"eval_steps_per_second": 2.71,
|
| 1064 |
+
"eval_wer": 0.999816883354697,
|
| 1065 |
+
"step": 9300
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 18.181994191674733,
|
| 1069 |
+
"eval_cer": 0.31535625057505434,
|
| 1070 |
+
"eval_loss": 0.6083632707595825,
|
| 1071 |
+
"eval_runtime": 237.956,
|
| 1072 |
+
"eval_samples_per_second": 22.95,
|
| 1073 |
+
"eval_steps_per_second": 2.87,
|
| 1074 |
+
"eval_wer": 1.0,
|
| 1075 |
+
"step": 9400
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 18.375605033881897,
|
| 1079 |
+
"grad_norm": 4.794497489929199,
|
| 1080 |
+
"learning_rate": 2.2788000000000003e-05,
|
| 1081 |
+
"loss": 0.5057,
|
| 1082 |
+
"step": 9500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 18.375605033881897,
|
| 1086 |
+
"eval_cer": 0.31467680177789104,
|
| 1087 |
+
"eval_loss": 0.6001758575439453,
|
| 1088 |
+
"eval_runtime": 227.7296,
|
| 1089 |
+
"eval_samples_per_second": 23.98,
|
| 1090 |
+
"eval_steps_per_second": 2.999,
|
| 1091 |
+
"eval_wer": 0.999816883354697,
|
| 1092 |
+
"step": 9500
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 18.56921587608906,
|
| 1096 |
+
"eval_cer": 0.31280123999405485,
|
| 1097 |
+
"eval_loss": 0.5875076055526733,
|
| 1098 |
+
"eval_runtime": 226.4211,
|
| 1099 |
+
"eval_samples_per_second": 24.119,
|
| 1100 |
+
"eval_steps_per_second": 3.017,
|
| 1101 |
+
"eval_wer": 1.0,
|
| 1102 |
+
"step": 9600
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 18.762826718296225,
|
| 1106 |
+
"eval_cer": 0.31375671486506573,
|
| 1107 |
+
"eval_loss": 0.5903081297874451,
|
| 1108 |
+
"eval_runtime": 227.027,
|
| 1109 |
+
"eval_samples_per_second": 24.054,
|
| 1110 |
+
"eval_steps_per_second": 3.008,
|
| 1111 |
+
"eval_wer": 0.999816883354697,
|
| 1112 |
+
"step": 9700
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 18.95643756050339,
|
| 1116 |
+
"eval_cer": 0.3126738433445867,
|
| 1117 |
+
"eval_loss": 0.5929713249206543,
|
| 1118 |
+
"eval_runtime": 243.7928,
|
| 1119 |
+
"eval_samples_per_second": 22.4,
|
| 1120 |
+
"eval_steps_per_second": 2.802,
|
| 1121 |
+
"eval_wer": 1.0,
|
| 1122 |
+
"step": 9800
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 19.149080348499517,
|
| 1126 |
+
"eval_cer": 0.31413890481347007,
|
| 1127 |
+
"eval_loss": 0.5854855179786682,
|
| 1128 |
+
"eval_runtime": 230.7398,
|
| 1129 |
+
"eval_samples_per_second": 23.667,
|
| 1130 |
+
"eval_steps_per_second": 2.96,
|
| 1131 |
+
"eval_wer": 1.0,
|
| 1132 |
+
"step": 9900
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 19.34269119070668,
|
| 1136 |
+
"grad_norm": 4.687788009643555,
|
| 1137 |
+
"learning_rate": 2.39856e-05,
|
| 1138 |
+
"loss": 0.4709,
|
| 1139 |
+
"step": 10000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 19.34269119070668,
|
| 1143 |
+
"eval_cer": 0.3119943945474234,
|
| 1144 |
+
"eval_loss": 0.5880363583564758,
|
| 1145 |
+
"eval_runtime": 227.5508,
|
| 1146 |
+
"eval_samples_per_second": 23.999,
|
| 1147 |
+
"eval_steps_per_second": 3.002,
|
| 1148 |
+
"eval_wer": 1.0,
|
| 1149 |
+
"step": 10000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.53630203291384,
|
| 1153 |
+
"eval_cer": 0.3131197316177251,
|
| 1154 |
+
"eval_loss": 0.5854519605636597,
|
| 1155 |
+
"eval_runtime": 235.4586,
|
| 1156 |
+
"eval_samples_per_second": 23.193,
|
| 1157 |
+
"eval_steps_per_second": 2.901,
|
| 1158 |
+
"eval_wer": 1.0,
|
| 1159 |
+
"step": 10100
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 19.729912875121006,
|
| 1163 |
+
"eval_cer": 0.310649652136371,
|
| 1164 |
+
"eval_loss": 0.5734274387359619,
|
| 1165 |
+
"eval_runtime": 227.5849,
|
| 1166 |
+
"eval_samples_per_second": 23.995,
|
| 1167 |
+
"eval_steps_per_second": 3.001,
|
| 1168 |
+
"eval_wer": 1.0,
|
| 1169 |
+
"step": 10200
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 19.92352371732817,
|
| 1173 |
+
"eval_cer": 0.31090444543530726,
|
| 1174 |
+
"eval_loss": 0.5776930451393127,
|
| 1175 |
+
"eval_runtime": 227.4224,
|
| 1176 |
+
"eval_samples_per_second": 24.013,
|
| 1177 |
+
"eval_steps_per_second": 3.003,
|
| 1178 |
+
"eval_wer": 1.0,
|
| 1179 |
+
"step": 10300
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 19.962245885769605,
|
| 1183 |
+
"step": 10320,
|
| 1184 |
+
"total_flos": 1.4589649587726338e+19,
|
| 1185 |
+
"train_loss": 5.084269817855007,
|
| 1186 |
+
"train_runtime": 64283.8792,
|
| 1187 |
+
"train_samples_per_second": 5.142,
|
| 1188 |
+
"train_steps_per_second": 0.161
|
| 1189 |
+
}
|
| 1190 |
+
],
|
| 1191 |
+
"logging_steps": 500,
|
| 1192 |
+
"max_steps": 10320,
|
| 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": 1.4589649587726338e+19,
|
| 1209 |
+
"train_batch_size": 16,
|
| 1210 |
+
"trial_name": null,
|
| 1211 |
+
"trial_params": null
|
| 1212 |
+
}
|