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-roma
|
| 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: 0.
|
| 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-roma
|
| 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: 0.3850
|
| 26 |
+
- Wer: 0.9984
|
| 27 |
+
- Cer: 0.1901
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_cer": 0.19008352196261202,
|
| 4 |
+
"eval_loss": 0.385017067193985,
|
| 5 |
+
"eval_runtime": 242.1765,
|
| 6 |
+
"eval_samples": 5459,
|
| 7 |
+
"eval_samples_per_second": 22.541,
|
| 8 |
+
"eval_steps_per_second": 2.82,
|
| 9 |
+
"eval_wer": 0.9983513464004397,
|
| 10 |
+
"total_flos": 1.4614133359859188e+19,
|
| 11 |
+
"train_loss": 1.9748668191050192,
|
| 12 |
+
"train_runtime": 66473.8913,
|
| 13 |
+
"train_samples": 16531,
|
| 14 |
+
"train_samples_per_second": 4.974,
|
| 15 |
+
"train_steps_per_second": 0.156
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_cer": 0.19008352196261202,
|
| 4 |
+
"eval_loss": 0.385017067193985,
|
| 5 |
+
"eval_runtime": 242.1765,
|
| 6 |
+
"eval_samples": 5459,
|
| 7 |
+
"eval_samples_per_second": 22.541,
|
| 8 |
+
"eval_steps_per_second": 2.82,
|
| 9 |
+
"eval_wer": 0.9983513464004397
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.4614133359859188e+19,
|
| 4 |
+
"train_loss": 1.9748668191050192,
|
| 5 |
+
"train_runtime": 66473.8913,
|
| 6 |
+
"train_samples": 16531,
|
| 7 |
+
"train_samples_per_second": 4.974,
|
| 8 |
+
"train_steps_per_second": 0.156
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.38558459281921387,
|
| 3 |
+
"best_model_checkpoint": "./Hubert-common_voice_JSUT-ja-demo-roma/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": 3.3906697851852106,
|
| 14 |
+
"eval_loss": 16.271892547607422,
|
| 15 |
+
"eval_runtime": 235.1592,
|
| 16 |
+
"eval_samples_per_second": 23.214,
|
| 17 |
+
"eval_steps_per_second": 2.904,
|
| 18 |
+
"eval_wer": 3.0917750503755266,
|
| 19 |
+
"step": 100
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.38684719535783363,
|
| 23 |
+
"eval_cer": 2.893664453340365,
|
| 24 |
+
"eval_loss": 16.005735397338867,
|
| 25 |
+
"eval_runtime": 236.1908,
|
| 26 |
+
"eval_samples_per_second": 23.113,
|
| 27 |
+
"eval_steps_per_second": 2.892,
|
| 28 |
+
"eval_wer": 2.8734200403004215,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.5802707930367504,
|
| 33 |
+
"eval_cer": 1.690616021560241,
|
| 34 |
+
"eval_loss": 15.374765396118164,
|
| 35 |
+
"eval_runtime": 231.2146,
|
| 36 |
+
"eval_samples_per_second": 23.61,
|
| 37 |
+
"eval_steps_per_second": 2.954,
|
| 38 |
+
"eval_wer": 1.9646455394760944,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.7736943907156673,
|
| 43 |
+
"eval_cer": 0.9291963879062664,
|
| 44 |
+
"eval_loss": 13.043855667114258,
|
| 45 |
+
"eval_runtime": 226.4398,
|
| 46 |
+
"eval_samples_per_second": 24.108,
|
| 47 |
+
"eval_steps_per_second": 3.016,
|
| 48 |
+
"eval_wer": 1.0,
|
| 49 |
+
"step": 400
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.9671179883945842,
|
| 53 |
+
"grad_norm": 47.46343994140625,
|
| 54 |
+
"learning_rate": 1.1904e-06,
|
| 55 |
+
"loss": 11.8785,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.9671179883945842,
|
| 60 |
+
"eval_cer": 0.929223783383958,
|
| 61 |
+
"eval_loss": 7.6484761238098145,
|
| 62 |
+
"eval_runtime": 226.1704,
|
| 63 |
+
"eval_samples_per_second": 24.137,
|
| 64 |
+
"eval_steps_per_second": 3.02,
|
| 65 |
+
"eval_wer": 1.0,
|
| 66 |
+
"step": 500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.1605415860735009,
|
| 70 |
+
"eval_cer": 0.929223783383958,
|
| 71 |
+
"eval_loss": 6.007350444793701,
|
| 72 |
+
"eval_runtime": 228.9926,
|
| 73 |
+
"eval_samples_per_second": 23.839,
|
| 74 |
+
"eval_steps_per_second": 2.983,
|
| 75 |
+
"eval_wer": 1.0,
|
| 76 |
+
"step": 600
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.3539651837524178,
|
| 80 |
+
"eval_cer": 0.929223783383958,
|
| 81 |
+
"eval_loss": 5.646536827087402,
|
| 82 |
+
"eval_runtime": 323.7978,
|
| 83 |
+
"eval_samples_per_second": 16.859,
|
| 84 |
+
"eval_steps_per_second": 2.109,
|
| 85 |
+
"eval_wer": 1.0,
|
| 86 |
+
"step": 700
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.5473887814313345,
|
| 90 |
+
"eval_cer": 0.929223783383958,
|
| 91 |
+
"eval_loss": 5.502617359161377,
|
| 92 |
+
"eval_runtime": 258.5966,
|
| 93 |
+
"eval_samples_per_second": 21.11,
|
| 94 |
+
"eval_steps_per_second": 2.641,
|
| 95 |
+
"eval_wer": 1.0,
|
| 96 |
+
"step": 800
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.7408123791102514,
|
| 100 |
+
"eval_cer": 0.929223783383958,
|
| 101 |
+
"eval_loss": 5.361776351928711,
|
| 102 |
+
"eval_runtime": 256.6054,
|
| 103 |
+
"eval_samples_per_second": 21.274,
|
| 104 |
+
"eval_steps_per_second": 2.662,
|
| 105 |
+
"eval_wer": 1.0,
|
| 106 |
+
"step": 900
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.9342359767891684,
|
| 110 |
+
"grad_norm": 29.7659969329834,
|
| 111 |
+
"learning_rate": 2.3904e-06,
|
| 112 |
+
"loss": 4.9912,
|
| 113 |
+
"step": 1000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.9342359767891684,
|
| 117 |
+
"eval_cer": 0.929223783383958,
|
| 118 |
+
"eval_loss": 5.219295024871826,
|
| 119 |
+
"eval_runtime": 262.3733,
|
| 120 |
+
"eval_samples_per_second": 20.806,
|
| 121 |
+
"eval_steps_per_second": 2.603,
|
| 122 |
+
"eval_wer": 1.0,
|
| 123 |
+
"step": 1000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.127659574468085,
|
| 127 |
+
"eval_cer": 0.929223783383958,
|
| 128 |
+
"eval_loss": 5.06879997253418,
|
| 129 |
+
"eval_runtime": 246.2278,
|
| 130 |
+
"eval_samples_per_second": 22.171,
|
| 131 |
+
"eval_steps_per_second": 2.774,
|
| 132 |
+
"eval_wer": 1.0,
|
| 133 |
+
"step": 1100
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.3210831721470018,
|
| 137 |
+
"eval_cer": 0.929223783383958,
|
| 138 |
+
"eval_loss": 4.91414737701416,
|
| 139 |
+
"eval_runtime": 265.8995,
|
| 140 |
+
"eval_samples_per_second": 20.53,
|
| 141 |
+
"eval_steps_per_second": 2.569,
|
| 142 |
+
"eval_wer": 1.0,
|
| 143 |
+
"step": 1200
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.514506769825919,
|
| 147 |
+
"eval_cer": 0.929223783383958,
|
| 148 |
+
"eval_loss": 4.753695964813232,
|
| 149 |
+
"eval_runtime": 261.3741,
|
| 150 |
+
"eval_samples_per_second": 20.886,
|
| 151 |
+
"eval_steps_per_second": 2.613,
|
| 152 |
+
"eval_wer": 1.0,
|
| 153 |
+
"step": 1300
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.7079303675048356,
|
| 157 |
+
"eval_cer": 0.929223783383958,
|
| 158 |
+
"eval_loss": 4.589428901672363,
|
| 159 |
+
"eval_runtime": 262.0559,
|
| 160 |
+
"eval_samples_per_second": 20.831,
|
| 161 |
+
"eval_steps_per_second": 2.606,
|
| 162 |
+
"eval_wer": 1.0,
|
| 163 |
+
"step": 1400
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.9013539651837523,
|
| 167 |
+
"grad_norm": 19.784141540527344,
|
| 168 |
+
"learning_rate": 3.5904e-06,
|
| 169 |
+
"loss": 4.3024,
|
| 170 |
+
"step": 1500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.9013539651837523,
|
| 174 |
+
"eval_cer": 0.929223783383958,
|
| 175 |
+
"eval_loss": 4.4225029945373535,
|
| 176 |
+
"eval_runtime": 247.2412,
|
| 177 |
+
"eval_samples_per_second": 22.08,
|
| 178 |
+
"eval_steps_per_second": 2.762,
|
| 179 |
+
"eval_wer": 1.0,
|
| 180 |
+
"step": 1500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.094777562862669,
|
| 184 |
+
"eval_cer": 0.929223783383958,
|
| 185 |
+
"eval_loss": 4.2562456130981445,
|
| 186 |
+
"eval_runtime": 265.0317,
|
| 187 |
+
"eval_samples_per_second": 20.598,
|
| 188 |
+
"eval_steps_per_second": 2.577,
|
| 189 |
+
"eval_wer": 1.0,
|
| 190 |
+
"step": 1600
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.288201160541586,
|
| 194 |
+
"eval_cer": 0.929223783383958,
|
| 195 |
+
"eval_loss": 4.094423770904541,
|
| 196 |
+
"eval_runtime": 262.7201,
|
| 197 |
+
"eval_samples_per_second": 20.779,
|
| 198 |
+
"eval_steps_per_second": 2.6,
|
| 199 |
+
"eval_wer": 1.0,
|
| 200 |
+
"step": 1700
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.481624758220503,
|
| 204 |
+
"eval_cer": 0.929223783383958,
|
| 205 |
+
"eval_loss": 3.9344263076782227,
|
| 206 |
+
"eval_runtime": 233.1037,
|
| 207 |
+
"eval_samples_per_second": 23.419,
|
| 208 |
+
"eval_steps_per_second": 2.93,
|
| 209 |
+
"eval_wer": 1.0,
|
| 210 |
+
"step": 1800
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.6750483558994196,
|
| 214 |
+
"eval_cer": 0.929223783383958,
|
| 215 |
+
"eval_loss": 3.7835137844085693,
|
| 216 |
+
"eval_runtime": 231.2092,
|
| 217 |
+
"eval_samples_per_second": 23.611,
|
| 218 |
+
"eval_steps_per_second": 2.954,
|
| 219 |
+
"eval_wer": 1.0,
|
| 220 |
+
"step": 1900
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.8684719535783367,
|
| 224 |
+
"grad_norm": 19.985584259033203,
|
| 225 |
+
"learning_rate": 4.7904e-06,
|
| 226 |
+
"loss": 3.6966,
|
| 227 |
+
"step": 2000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.8684719535783367,
|
| 231 |
+
"eval_cer": 0.929223783383958,
|
| 232 |
+
"eval_loss": 3.641073703765869,
|
| 233 |
+
"eval_runtime": 230.0297,
|
| 234 |
+
"eval_samples_per_second": 23.732,
|
| 235 |
+
"eval_steps_per_second": 2.969,
|
| 236 |
+
"eval_wer": 1.0,
|
| 237 |
+
"step": 2000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.061895551257253,
|
| 241 |
+
"eval_cer": 0.929223783383958,
|
| 242 |
+
"eval_loss": 3.5155856609344482,
|
| 243 |
+
"eval_runtime": 229.2143,
|
| 244 |
+
"eval_samples_per_second": 23.816,
|
| 245 |
+
"eval_steps_per_second": 2.98,
|
| 246 |
+
"eval_wer": 1.0,
|
| 247 |
+
"step": 2100
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 4.25531914893617,
|
| 251 |
+
"eval_cer": 0.929223783383958,
|
| 252 |
+
"eval_loss": 3.397294044494629,
|
| 253 |
+
"eval_runtime": 229.4391,
|
| 254 |
+
"eval_samples_per_second": 23.793,
|
| 255 |
+
"eval_steps_per_second": 2.977,
|
| 256 |
+
"eval_wer": 1.0,
|
| 257 |
+
"step": 2200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 4.448742746615087,
|
| 261 |
+
"eval_cer": 0.929223783383958,
|
| 262 |
+
"eval_loss": 3.290855646133423,
|
| 263 |
+
"eval_runtime": 231.2121,
|
| 264 |
+
"eval_samples_per_second": 23.61,
|
| 265 |
+
"eval_steps_per_second": 2.954,
|
| 266 |
+
"eval_wer": 1.0,
|
| 267 |
+
"step": 2300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.6421663442940035,
|
| 271 |
+
"eval_cer": 0.929223783383958,
|
| 272 |
+
"eval_loss": 3.1956613063812256,
|
| 273 |
+
"eval_runtime": 230.2419,
|
| 274 |
+
"eval_samples_per_second": 23.71,
|
| 275 |
+
"eval_steps_per_second": 2.966,
|
| 276 |
+
"eval_wer": 1.0,
|
| 277 |
+
"step": 2400
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.835589941972921,
|
| 281 |
+
"grad_norm": 3.1049797534942627,
|
| 282 |
+
"learning_rate": 5.9904e-06,
|
| 283 |
+
"loss": 3.2011,
|
| 284 |
+
"step": 2500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.835589941972921,
|
| 288 |
+
"eval_cer": 0.929223783383958,
|
| 289 |
+
"eval_loss": 3.115924596786499,
|
| 290 |
+
"eval_runtime": 231.315,
|
| 291 |
+
"eval_samples_per_second": 23.6,
|
| 292 |
+
"eval_steps_per_second": 2.953,
|
| 293 |
+
"eval_wer": 1.0,
|
| 294 |
+
"step": 2500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.029013539651838,
|
| 298 |
+
"eval_cer": 0.929223783383958,
|
| 299 |
+
"eval_loss": 3.0544307231903076,
|
| 300 |
+
"eval_runtime": 231.5463,
|
| 301 |
+
"eval_samples_per_second": 23.576,
|
| 302 |
+
"eval_steps_per_second": 2.95,
|
| 303 |
+
"eval_wer": 1.0,
|
| 304 |
+
"step": 2600
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.222437137330754,
|
| 308 |
+
"eval_cer": 0.929223783383958,
|
| 309 |
+
"eval_loss": 3.0038533210754395,
|
| 310 |
+
"eval_runtime": 237.992,
|
| 311 |
+
"eval_samples_per_second": 22.938,
|
| 312 |
+
"eval_steps_per_second": 2.87,
|
| 313 |
+
"eval_wer": 1.0,
|
| 314 |
+
"step": 2700
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.415860735009671,
|
| 318 |
+
"eval_cer": 0.929223783383958,
|
| 319 |
+
"eval_loss": 2.9653820991516113,
|
| 320 |
+
"eval_runtime": 231.2651,
|
| 321 |
+
"eval_samples_per_second": 23.605,
|
| 322 |
+
"eval_steps_per_second": 2.953,
|
| 323 |
+
"eval_wer": 1.0,
|
| 324 |
+
"step": 2800
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.609284332688588,
|
| 328 |
+
"eval_cer": 0.929223783383958,
|
| 329 |
+
"eval_loss": 2.9386982917785645,
|
| 330 |
+
"eval_runtime": 235.1119,
|
| 331 |
+
"eval_samples_per_second": 23.219,
|
| 332 |
+
"eval_steps_per_second": 2.905,
|
| 333 |
+
"eval_wer": 1.0,
|
| 334 |
+
"step": 2900
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 5.802707930367505,
|
| 338 |
+
"grad_norm": 0.9443885684013367,
|
| 339 |
+
"learning_rate": 7.190400000000001e-06,
|
| 340 |
+
"loss": 2.9439,
|
| 341 |
+
"step": 3000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 5.802707930367505,
|
| 345 |
+
"eval_cer": 0.929223783383958,
|
| 346 |
+
"eval_loss": 2.9090564250946045,
|
| 347 |
+
"eval_runtime": 234.7068,
|
| 348 |
+
"eval_samples_per_second": 23.259,
|
| 349 |
+
"eval_steps_per_second": 2.91,
|
| 350 |
+
"eval_wer": 1.0,
|
| 351 |
+
"step": 3000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.996131528046422,
|
| 355 |
+
"eval_cer": 0.929223783383958,
|
| 356 |
+
"eval_loss": 2.8868346214294434,
|
| 357 |
+
"eval_runtime": 233.0298,
|
| 358 |
+
"eval_samples_per_second": 23.426,
|
| 359 |
+
"eval_steps_per_second": 2.931,
|
| 360 |
+
"eval_wer": 1.0,
|
| 361 |
+
"step": 3100
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 6.189555125725338,
|
| 365 |
+
"eval_cer": 0.929223783383958,
|
| 366 |
+
"eval_loss": 2.8660459518432617,
|
| 367 |
+
"eval_runtime": 237.6658,
|
| 368 |
+
"eval_samples_per_second": 22.969,
|
| 369 |
+
"eval_steps_per_second": 2.874,
|
| 370 |
+
"eval_wer": 1.0,
|
| 371 |
+
"step": 3200
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 6.382978723404255,
|
| 375 |
+
"eval_cer": 0.929223783383958,
|
| 376 |
+
"eval_loss": 2.853316068649292,
|
| 377 |
+
"eval_runtime": 238.1324,
|
| 378 |
+
"eval_samples_per_second": 22.924,
|
| 379 |
+
"eval_steps_per_second": 2.868,
|
| 380 |
+
"eval_wer": 1.0,
|
| 381 |
+
"step": 3300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 6.576402321083172,
|
| 385 |
+
"eval_cer": 0.929223783383958,
|
| 386 |
+
"eval_loss": 2.7336666584014893,
|
| 387 |
+
"eval_runtime": 248.0434,
|
| 388 |
+
"eval_samples_per_second": 22.008,
|
| 389 |
+
"eval_steps_per_second": 2.754,
|
| 390 |
+
"eval_wer": 1.0,
|
| 391 |
+
"step": 3400
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 6.769825918762089,
|
| 395 |
+
"grad_norm": 5.135930061340332,
|
| 396 |
+
"learning_rate": 8.3904e-06,
|
| 397 |
+
"loss": 2.7884,
|
| 398 |
+
"step": 3500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.769825918762089,
|
| 402 |
+
"eval_cer": 0.929223783383958,
|
| 403 |
+
"eval_loss": 2.523024559020996,
|
| 404 |
+
"eval_runtime": 234.9913,
|
| 405 |
+
"eval_samples_per_second": 23.231,
|
| 406 |
+
"eval_steps_per_second": 2.906,
|
| 407 |
+
"eval_wer": 1.0,
|
| 408 |
+
"step": 3500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 6.963249516441006,
|
| 412 |
+
"eval_cer": 0.9181765570048525,
|
| 413 |
+
"eval_loss": 2.272446870803833,
|
| 414 |
+
"eval_runtime": 233.6368,
|
| 415 |
+
"eval_samples_per_second": 23.365,
|
| 416 |
+
"eval_steps_per_second": 2.923,
|
| 417 |
+
"eval_wer": 1.0,
|
| 418 |
+
"step": 3600
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 7.156673114119923,
|
| 422 |
+
"eval_cer": 0.6315890404391495,
|
| 423 |
+
"eval_loss": 1.9632701873779297,
|
| 424 |
+
"eval_runtime": 237.5728,
|
| 425 |
+
"eval_samples_per_second": 22.978,
|
| 426 |
+
"eval_steps_per_second": 2.875,
|
| 427 |
+
"eval_wer": 1.0,
|
| 428 |
+
"step": 3700
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.350096711798839,
|
| 432 |
+
"eval_cer": 0.4242155476184769,
|
| 433 |
+
"eval_loss": 1.5858280658721924,
|
| 434 |
+
"eval_runtime": 277.2902,
|
| 435 |
+
"eval_samples_per_second": 19.687,
|
| 436 |
+
"eval_steps_per_second": 2.463,
|
| 437 |
+
"eval_wer": 1.0,
|
| 438 |
+
"step": 3800
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 7.543520309477756,
|
| 442 |
+
"eval_cer": 0.3861015892801496,
|
| 443 |
+
"eval_loss": 1.351006031036377,
|
| 444 |
+
"eval_runtime": 236.5551,
|
| 445 |
+
"eval_samples_per_second": 23.077,
|
| 446 |
+
"eval_steps_per_second": 2.887,
|
| 447 |
+
"eval_wer": 0.9998168162667155,
|
| 448 |
+
"step": 3900
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 7.7369439071566735,
|
| 452 |
+
"grad_norm": 3.2181670665740967,
|
| 453 |
+
"learning_rate": 9.5904e-06,
|
| 454 |
+
"loss": 1.7651,
|
| 455 |
+
"step": 4000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 7.7369439071566735,
|
| 459 |
+
"eval_cer": 0.33344405672233657,
|
| 460 |
+
"eval_loss": 1.1917191743850708,
|
| 461 |
+
"eval_runtime": 237.0965,
|
| 462 |
+
"eval_samples_per_second": 23.024,
|
| 463 |
+
"eval_steps_per_second": 2.881,
|
| 464 |
+
"eval_wer": 0.999267265066862,
|
| 465 |
+
"step": 4000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.93036750483559,
|
| 469 |
+
"eval_cer": 0.29824771675815615,
|
| 470 |
+
"eval_loss": 1.0715813636779785,
|
| 471 |
+
"eval_runtime": 240.0983,
|
| 472 |
+
"eval_samples_per_second": 22.737,
|
| 473 |
+
"eval_steps_per_second": 2.845,
|
| 474 |
+
"eval_wer": 0.9979849789338707,
|
| 475 |
+
"step": 4100
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 8.123791102514506,
|
| 479 |
+
"eval_cer": 0.27819422708796343,
|
| 480 |
+
"eval_loss": 0.9761540293693542,
|
| 481 |
+
"eval_runtime": 238.5129,
|
| 482 |
+
"eval_samples_per_second": 22.888,
|
| 483 |
+
"eval_steps_per_second": 2.864,
|
| 484 |
+
"eval_wer": 0.9976186114673017,
|
| 485 |
+
"step": 4200
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 8.317214700193423,
|
| 489 |
+
"eval_cer": 0.2595721511271527,
|
| 490 |
+
"eval_loss": 0.904407799243927,
|
| 491 |
+
"eval_runtime": 234.8451,
|
| 492 |
+
"eval_samples_per_second": 23.245,
|
| 493 |
+
"eval_steps_per_second": 2.908,
|
| 494 |
+
"eval_wer": 0.9965195090675948,
|
| 495 |
+
"step": 4300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.51063829787234,
|
| 499 |
+
"eval_cer": 0.2565654974505084,
|
| 500 |
+
"eval_loss": 0.8529276251792908,
|
| 501 |
+
"eval_runtime": 237.5826,
|
| 502 |
+
"eval_samples_per_second": 22.977,
|
| 503 |
+
"eval_steps_per_second": 2.875,
|
| 504 |
+
"eval_wer": 0.9963363253343103,
|
| 505 |
+
"step": 4400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 8.704061895551257,
|
| 509 |
+
"grad_norm": 2.711160898208618,
|
| 510 |
+
"learning_rate": 1.0790400000000001e-05,
|
| 511 |
+
"loss": 0.9278,
|
| 512 |
+
"step": 4500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.704061895551257,
|
| 516 |
+
"eval_cer": 0.2466140901790637,
|
| 517 |
+
"eval_loss": 0.7957596182823181,
|
| 518 |
+
"eval_runtime": 234.6716,
|
| 519 |
+
"eval_samples_per_second": 23.262,
|
| 520 |
+
"eval_steps_per_second": 2.91,
|
| 521 |
+
"eval_wer": 0.9970690602674482,
|
| 522 |
+
"step": 4500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 8.897485493230175,
|
| 526 |
+
"eval_cer": 0.24351497676521047,
|
| 527 |
+
"eval_loss": 0.7534636855125427,
|
| 528 |
+
"eval_runtime": 235.3455,
|
| 529 |
+
"eval_samples_per_second": 23.196,
|
| 530 |
+
"eval_steps_per_second": 2.902,
|
| 531 |
+
"eval_wer": 0.9965195090675948,
|
| 532 |
+
"step": 4600
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 9.090909090909092,
|
| 536 |
+
"eval_cer": 0.24028573483232255,
|
| 537 |
+
"eval_loss": 0.7190229296684265,
|
| 538 |
+
"eval_runtime": 235.8068,
|
| 539 |
+
"eval_samples_per_second": 23.15,
|
| 540 |
+
"eval_steps_per_second": 2.896,
|
| 541 |
+
"eval_wer": 0.9974354277340172,
|
| 542 |
+
"step": 4700
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 9.284332688588007,
|
| 546 |
+
"eval_cer": 0.2355908348429383,
|
| 547 |
+
"eval_loss": 0.6800413727760315,
|
| 548 |
+
"eval_runtime": 236.222,
|
| 549 |
+
"eval_samples_per_second": 23.11,
|
| 550 |
+
"eval_steps_per_second": 2.891,
|
| 551 |
+
"eval_wer": 0.9974354277340172,
|
| 552 |
+
"step": 4800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 9.477756286266924,
|
| 556 |
+
"eval_cer": 0.23300196220108965,
|
| 557 |
+
"eval_loss": 0.6568382978439331,
|
| 558 |
+
"eval_runtime": 236.9709,
|
| 559 |
+
"eval_samples_per_second": 23.037,
|
| 560 |
+
"eval_steps_per_second": 2.882,
|
| 561 |
+
"eval_wer": 0.9963363253343103,
|
| 562 |
+
"step": 4900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 9.671179883945841,
|
| 566 |
+
"grad_norm": 5.1745381355285645,
|
| 567 |
+
"learning_rate": 1.19904e-05,
|
| 568 |
+
"loss": 0.6673,
|
| 569 |
+
"step": 5000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 9.671179883945841,
|
| 573 |
+
"eval_cer": 0.23294032237628373,
|
| 574 |
+
"eval_loss": 0.6317699551582336,
|
| 575 |
+
"eval_runtime": 235.798,
|
| 576 |
+
"eval_samples_per_second": 23.151,
|
| 577 |
+
"eval_steps_per_second": 2.897,
|
| 578 |
+
"eval_wer": 0.9959699578677413,
|
| 579 |
+
"step": 5000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.864603481624759,
|
| 583 |
+
"eval_cer": 0.22926932836562006,
|
| 584 |
+
"eval_loss": 0.613182783126831,
|
| 585 |
+
"eval_runtime": 236.7731,
|
| 586 |
+
"eval_samples_per_second": 23.056,
|
| 587 |
+
"eval_steps_per_second": 2.885,
|
| 588 |
+
"eval_wer": 0.9972522440007328,
|
| 589 |
+
"step": 5100
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 10.058027079303676,
|
| 593 |
+
"eval_cer": 0.2261496683434982,
|
| 594 |
+
"eval_loss": 0.5896427631378174,
|
| 595 |
+
"eval_runtime": 236.3817,
|
| 596 |
+
"eval_samples_per_second": 23.094,
|
| 597 |
+
"eval_steps_per_second": 2.889,
|
| 598 |
+
"eval_wer": 0.9970690602674482,
|
| 599 |
+
"step": 5200
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 10.251450676982591,
|
| 603 |
+
"eval_cer": 0.22313274136271954,
|
| 604 |
+
"eval_loss": 0.5742546916007996,
|
| 605 |
+
"eval_runtime": 234.8696,
|
| 606 |
+
"eval_samples_per_second": 23.243,
|
| 607 |
+
"eval_steps_per_second": 2.908,
|
| 608 |
+
"eval_wer": 0.9961531416010259,
|
| 609 |
+
"step": 5300
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.444874274661508,
|
| 613 |
+
"eval_cer": 0.2214684660929597,
|
| 614 |
+
"eval_loss": 0.5562453866004944,
|
| 615 |
+
"eval_runtime": 234.6327,
|
| 616 |
+
"eval_samples_per_second": 23.266,
|
| 617 |
+
"eval_steps_per_second": 2.911,
|
| 618 |
+
"eval_wer": 0.9959699578677413,
|
| 619 |
+
"step": 5400
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 10.638297872340425,
|
| 623 |
+
"grad_norm": 3.1148133277893066,
|
| 624 |
+
"learning_rate": 1.31904e-05,
|
| 625 |
+
"loss": 0.5392,
|
| 626 |
+
"step": 5500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 10.638297872340425,
|
| 630 |
+
"eval_cer": 0.2236943486553957,
|
| 631 |
+
"eval_loss": 0.5472539067268372,
|
| 632 |
+
"eval_runtime": 233.6555,
|
| 633 |
+
"eval_samples_per_second": 23.363,
|
| 634 |
+
"eval_steps_per_second": 2.923,
|
| 635 |
+
"eval_wer": 0.9972522440007328,
|
| 636 |
+
"step": 5500
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 10.831721470019342,
|
| 640 |
+
"eval_cer": 0.21852002780640986,
|
| 641 |
+
"eval_loss": 0.5307034850120544,
|
| 642 |
+
"eval_runtime": 233.484,
|
| 643 |
+
"eval_samples_per_second": 23.381,
|
| 644 |
+
"eval_steps_per_second": 2.925,
|
| 645 |
+
"eval_wer": 0.9963363253343103,
|
| 646 |
+
"step": 5600
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 11.02514506769826,
|
| 650 |
+
"eval_cer": 0.21733859783096304,
|
| 651 |
+
"eval_loss": 0.5194967985153198,
|
| 652 |
+
"eval_runtime": 235.0242,
|
| 653 |
+
"eval_samples_per_second": 23.227,
|
| 654 |
+
"eval_steps_per_second": 2.906,
|
| 655 |
+
"eval_wer": 0.9976186114673017,
|
| 656 |
+
"step": 5700
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 11.218568665377177,
|
| 660 |
+
"eval_cer": 0.21635578506877978,
|
| 661 |
+
"eval_loss": 0.5090118050575256,
|
| 662 |
+
"eval_runtime": 234.9867,
|
| 663 |
+
"eval_samples_per_second": 23.231,
|
| 664 |
+
"eval_steps_per_second": 2.907,
|
| 665 |
+
"eval_wer": 0.9978017952005862,
|
| 666 |
+
"step": 5800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 11.411992263056092,
|
| 670 |
+
"eval_cer": 0.21347583547645874,
|
| 671 |
+
"eval_loss": 0.4978716969490051,
|
| 672 |
+
"eval_runtime": 235.5271,
|
| 673 |
+
"eval_samples_per_second": 23.178,
|
| 674 |
+
"eval_steps_per_second": 2.9,
|
| 675 |
+
"eval_wer": 0.9974354277340172,
|
| 676 |
+
"step": 5900
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 11.60541586073501,
|
| 680 |
+
"grad_norm": 2.333935499191284,
|
| 681 |
+
"learning_rate": 1.43904e-05,
|
| 682 |
+
"loss": 0.4572,
|
| 683 |
+
"step": 6000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 11.60541586073501,
|
| 687 |
+
"eval_cer": 0.21267451775398177,
|
| 688 |
+
"eval_loss": 0.49008145928382874,
|
| 689 |
+
"eval_runtime": 235.4425,
|
| 690 |
+
"eval_samples_per_second": 23.186,
|
| 691 |
+
"eval_steps_per_second": 2.901,
|
| 692 |
+
"eval_wer": 0.9974354277340172,
|
| 693 |
+
"step": 6000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.798839458413926,
|
| 697 |
+
"eval_cer": 0.21371212147154808,
|
| 698 |
+
"eval_loss": 0.487173467874527,
|
| 699 |
+
"eval_runtime": 235.8902,
|
| 700 |
+
"eval_samples_per_second": 23.142,
|
| 701 |
+
"eval_steps_per_second": 2.895,
|
| 702 |
+
"eval_wer": 0.999267265066862,
|
| 703 |
+
"step": 6100
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 11.992263056092844,
|
| 707 |
+
"eval_cer": 0.211890322205062,
|
| 708 |
+
"eval_loss": 0.4753509759902954,
|
| 709 |
+
"eval_runtime": 236.7331,
|
| 710 |
+
"eval_samples_per_second": 23.06,
|
| 711 |
+
"eval_steps_per_second": 2.885,
|
| 712 |
+
"eval_wer": 0.9972522440007328,
|
| 713 |
+
"step": 6200
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 12.18568665377176,
|
| 717 |
+
"eval_cer": 0.21195538646457937,
|
| 718 |
+
"eval_loss": 0.47239425778388977,
|
| 719 |
+
"eval_runtime": 236.344,
|
| 720 |
+
"eval_samples_per_second": 23.098,
|
| 721 |
+
"eval_steps_per_second": 2.89,
|
| 722 |
+
"eval_wer": 0.9968858765341637,
|
| 723 |
+
"step": 6300
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.379110251450676,
|
| 727 |
+
"eval_cer": 0.20878093548707446,
|
| 728 |
+
"eval_loss": 0.4649977684020996,
|
| 729 |
+
"eval_runtime": 242.8375,
|
| 730 |
+
"eval_samples_per_second": 22.48,
|
| 731 |
+
"eval_steps_per_second": 2.813,
|
| 732 |
+
"eval_wer": 0.9987177138670086,
|
| 733 |
+
"step": 6400
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 12.572533849129593,
|
| 737 |
+
"grad_norm": 3.1772515773773193,
|
| 738 |
+
"learning_rate": 1.5590400000000002e-05,
|
| 739 |
+
"loss": 0.41,
|
| 740 |
+
"step": 6500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 12.572533849129593,
|
| 744 |
+
"eval_cer": 0.20764744759758783,
|
| 745 |
+
"eval_loss": 0.4591744542121887,
|
| 746 |
+
"eval_runtime": 237.1668,
|
| 747 |
+
"eval_samples_per_second": 23.018,
|
| 748 |
+
"eval_steps_per_second": 2.88,
|
| 749 |
+
"eval_wer": 0.9976186114673017,
|
| 750 |
+
"step": 6500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 12.76595744680851,
|
| 754 |
+
"eval_cer": 0.20641122666675799,
|
| 755 |
+
"eval_loss": 0.4502531886100769,
|
| 756 |
+
"eval_runtime": 237.1617,
|
| 757 |
+
"eval_samples_per_second": 23.018,
|
| 758 |
+
"eval_steps_per_second": 2.88,
|
| 759 |
+
"eval_wer": 0.9981681626671551,
|
| 760 |
+
"step": 6600
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 12.959381044487428,
|
| 764 |
+
"eval_cer": 0.20994524328896408,
|
| 765 |
+
"eval_loss": 0.44779568910598755,
|
| 766 |
+
"eval_runtime": 236.6236,
|
| 767 |
+
"eval_samples_per_second": 23.07,
|
| 768 |
+
"eval_steps_per_second": 2.886,
|
| 769 |
+
"eval_wer": 0.9963363253343103,
|
| 770 |
+
"step": 6700
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 13.152804642166345,
|
| 774 |
+
"eval_cer": 0.2061133008468627,
|
| 775 |
+
"eval_loss": 0.4495759606361389,
|
| 776 |
+
"eval_runtime": 237.3684,
|
| 777 |
+
"eval_samples_per_second": 22.998,
|
| 778 |
+
"eval_steps_per_second": 2.877,
|
| 779 |
+
"eval_wer": 0.9981681626671551,
|
| 780 |
+
"step": 6800
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 13.346228239845262,
|
| 784 |
+
"eval_cer": 0.20519897677890822,
|
| 785 |
+
"eval_loss": 0.443766713142395,
|
| 786 |
+
"eval_runtime": 251.4879,
|
| 787 |
+
"eval_samples_per_second": 21.707,
|
| 788 |
+
"eval_steps_per_second": 2.716,
|
| 789 |
+
"eval_wer": 0.9981681626671551,
|
| 790 |
+
"step": 6900
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 13.539651837524177,
|
| 794 |
+
"grad_norm": 2.66337513923645,
|
| 795 |
+
"learning_rate": 1.6790399999999998e-05,
|
| 796 |
+
"loss": 0.3688,
|
| 797 |
+
"step": 7000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 13.539651837524177,
|
| 801 |
+
"eval_cer": 0.20395933141336695,
|
| 802 |
+
"eval_loss": 0.4365153908729553,
|
| 803 |
+
"eval_runtime": 238.8337,
|
| 804 |
+
"eval_samples_per_second": 22.857,
|
| 805 |
+
"eval_steps_per_second": 2.86,
|
| 806 |
+
"eval_wer": 0.9990840813335776,
|
| 807 |
+
"step": 7000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.733075435203094,
|
| 811 |
+
"eval_cer": 0.20464421835565494,
|
| 812 |
+
"eval_loss": 0.4288468062877655,
|
| 813 |
+
"eval_runtime": 234.5955,
|
| 814 |
+
"eval_samples_per_second": 23.27,
|
| 815 |
+
"eval_steps_per_second": 2.911,
|
| 816 |
+
"eval_wer": 0.9979849789338707,
|
| 817 |
+
"step": 7100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 13.926499032882012,
|
| 821 |
+
"eval_cer": 0.20250394666100494,
|
| 822 |
+
"eval_loss": 0.4299309551715851,
|
| 823 |
+
"eval_runtime": 237.0206,
|
| 824 |
+
"eval_samples_per_second": 23.032,
|
| 825 |
+
"eval_steps_per_second": 2.882,
|
| 826 |
+
"eval_wer": 0.9981681626671551,
|
| 827 |
+
"step": 7200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 14.119922630560929,
|
| 831 |
+
"eval_cer": 0.20263407518003965,
|
| 832 |
+
"eval_loss": 0.4274175465106964,
|
| 833 |
+
"eval_runtime": 237.1451,
|
| 834 |
+
"eval_samples_per_second": 23.02,
|
| 835 |
+
"eval_steps_per_second": 2.88,
|
| 836 |
+
"eval_wer": 0.9985345301337242,
|
| 837 |
+
"step": 7300
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.313346228239846,
|
| 841 |
+
"eval_cer": 0.20056229217961846,
|
| 842 |
+
"eval_loss": 0.42421066761016846,
|
| 843 |
+
"eval_runtime": 244.6511,
|
| 844 |
+
"eval_samples_per_second": 22.313,
|
| 845 |
+
"eval_steps_per_second": 2.792,
|
| 846 |
+
"eval_wer": 0.9983513464004397,
|
| 847 |
+
"step": 7400
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 14.506769825918763,
|
| 851 |
+
"grad_norm": 1.9870613813400269,
|
| 852 |
+
"learning_rate": 1.79904e-05,
|
| 853 |
+
"loss": 0.3394,
|
| 854 |
+
"step": 7500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 14.506769825918763,
|
| 858 |
+
"eval_cer": 0.20014108671011133,
|
| 859 |
+
"eval_loss": 0.4253482520580292,
|
| 860 |
+
"eval_runtime": 244.8721,
|
| 861 |
+
"eval_samples_per_second": 22.293,
|
| 862 |
+
"eval_steps_per_second": 2.789,
|
| 863 |
+
"eval_wer": 0.9970690602674482,
|
| 864 |
+
"step": 7500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 14.700193423597678,
|
| 868 |
+
"eval_cer": 0.19957263054801228,
|
| 869 |
+
"eval_loss": 0.4177948236465454,
|
| 870 |
+
"eval_runtime": 234.464,
|
| 871 |
+
"eval_samples_per_second": 23.283,
|
| 872 |
+
"eval_steps_per_second": 2.913,
|
| 873 |
+
"eval_wer": 0.9974354277340172,
|
| 874 |
+
"step": 7600
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 14.893617021276595,
|
| 878 |
+
"eval_cer": 0.20044928583414093,
|
| 879 |
+
"eval_loss": 0.41819530725479126,
|
| 880 |
+
"eval_runtime": 240.7737,
|
| 881 |
+
"eval_samples_per_second": 22.673,
|
| 882 |
+
"eval_steps_per_second": 2.837,
|
| 883 |
+
"eval_wer": 0.9983513464004397,
|
| 884 |
+
"step": 7700
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 15.087040618955513,
|
| 888 |
+
"eval_cer": 0.1979117797129639,
|
| 889 |
+
"eval_loss": 0.41940802335739136,
|
| 890 |
+
"eval_runtime": 239.6423,
|
| 891 |
+
"eval_samples_per_second": 22.78,
|
| 892 |
+
"eval_steps_per_second": 2.85,
|
| 893 |
+
"eval_wer": 0.9970690602674482,
|
| 894 |
+
"step": 7800
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 15.28046421663443,
|
| 898 |
+
"eval_cer": 0.19965481698108684,
|
| 899 |
+
"eval_loss": 0.416002482175827,
|
| 900 |
+
"eval_runtime": 233.6247,
|
| 901 |
+
"eval_samples_per_second": 23.367,
|
| 902 |
+
"eval_steps_per_second": 2.923,
|
| 903 |
+
"eval_wer": 0.9978017952005862,
|
| 904 |
+
"step": 7900
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 15.473887814313347,
|
| 908 |
+
"grad_norm": 3.6397812366485596,
|
| 909 |
+
"learning_rate": 1.9190400000000002e-05,
|
| 910 |
+
"loss": 0.3157,
|
| 911 |
+
"step": 8000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 15.473887814313347,
|
| 915 |
+
"eval_cer": 0.20096637547556837,
|
| 916 |
+
"eval_loss": 0.40957844257354736,
|
| 917 |
+
"eval_runtime": 233.3898,
|
| 918 |
+
"eval_samples_per_second": 23.39,
|
| 919 |
+
"eval_steps_per_second": 2.926,
|
| 920 |
+
"eval_wer": 0.9974354277340172,
|
| 921 |
+
"step": 8000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.667311411992262,
|
| 925 |
+
"eval_cer": 0.19801108831959563,
|
| 926 |
+
"eval_loss": 0.40878182649612427,
|
| 927 |
+
"eval_runtime": 233.2723,
|
| 928 |
+
"eval_samples_per_second": 23.402,
|
| 929 |
+
"eval_steps_per_second": 2.928,
|
| 930 |
+
"eval_wer": 0.9978017952005862,
|
| 931 |
+
"step": 8100
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 15.86073500967118,
|
| 935 |
+
"eval_cer": 0.19737414346326781,
|
| 936 |
+
"eval_loss": 0.4118936359882355,
|
| 937 |
+
"eval_runtime": 235.4949,
|
| 938 |
+
"eval_samples_per_second": 23.181,
|
| 939 |
+
"eval_steps_per_second": 2.9,
|
| 940 |
+
"eval_wer": 0.9983513464004397,
|
| 941 |
+
"step": 8200
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 16.054158607350097,
|
| 945 |
+
"eval_cer": 0.1965180347854078,
|
| 946 |
+
"eval_loss": 0.40991291403770447,
|
| 947 |
+
"eval_runtime": 243.05,
|
| 948 |
+
"eval_samples_per_second": 22.46,
|
| 949 |
+
"eval_steps_per_second": 2.81,
|
| 950 |
+
"eval_wer": 0.9983513464004397,
|
| 951 |
+
"step": 8300
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 16.247582205029012,
|
| 955 |
+
"eval_cer": 0.19766864484845165,
|
| 956 |
+
"eval_loss": 0.4085560739040375,
|
| 957 |
+
"eval_runtime": 232.1832,
|
| 958 |
+
"eval_samples_per_second": 23.512,
|
| 959 |
+
"eval_steps_per_second": 2.942,
|
| 960 |
+
"eval_wer": 0.9985345301337242,
|
| 961 |
+
"step": 8400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 16.44100580270793,
|
| 965 |
+
"grad_norm": 2.502861976623535,
|
| 966 |
+
"learning_rate": 2.03904e-05,
|
| 967 |
+
"loss": 0.2917,
|
| 968 |
+
"step": 8500
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 16.44100580270793,
|
| 972 |
+
"eval_cer": 0.19676116964992005,
|
| 973 |
+
"eval_loss": 0.40965768694877625,
|
| 974 |
+
"eval_runtime": 233.1901,
|
| 975 |
+
"eval_samples_per_second": 23.41,
|
| 976 |
+
"eval_steps_per_second": 2.929,
|
| 977 |
+
"eval_wer": 0.9983513464004397,
|
| 978 |
+
"step": 8500
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 16.634429400386846,
|
| 982 |
+
"eval_cer": 0.19489485273218524,
|
| 983 |
+
"eval_loss": 0.41127797961235046,
|
| 984 |
+
"eval_runtime": 235.9189,
|
| 985 |
+
"eval_samples_per_second": 23.139,
|
| 986 |
+
"eval_steps_per_second": 2.895,
|
| 987 |
+
"eval_wer": 0.9979849789338707,
|
| 988 |
+
"step": 8600
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 16.827852998065765,
|
| 992 |
+
"eval_cer": 0.19560713515216477,
|
| 993 |
+
"eval_loss": 0.40175729990005493,
|
| 994 |
+
"eval_runtime": 236.2968,
|
| 995 |
+
"eval_samples_per_second": 23.102,
|
| 996 |
+
"eval_steps_per_second": 2.89,
|
| 997 |
+
"eval_wer": 0.9983513464004397,
|
| 998 |
+
"step": 8700
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 17.02127659574468,
|
| 1002 |
+
"eval_cer": 0.19336413041617154,
|
| 1003 |
+
"eval_loss": 0.4042558968067169,
|
| 1004 |
+
"eval_runtime": 232.2491,
|
| 1005 |
+
"eval_samples_per_second": 23.505,
|
| 1006 |
+
"eval_steps_per_second": 2.941,
|
| 1007 |
+
"eval_wer": 0.9983513464004397,
|
| 1008 |
+
"step": 8800
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 17.214700193423596,
|
| 1012 |
+
"eval_cer": 0.19456953143459843,
|
| 1013 |
+
"eval_loss": 0.4046263098716736,
|
| 1014 |
+
"eval_runtime": 233.5316,
|
| 1015 |
+
"eval_samples_per_second": 23.376,
|
| 1016 |
+
"eval_steps_per_second": 2.925,
|
| 1017 |
+
"eval_wer": 0.9979849789338707,
|
| 1018 |
+
"step": 8900
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 17.408123791102515,
|
| 1022 |
+
"grad_norm": 1.7895680665969849,
|
| 1023 |
+
"learning_rate": 2.15904e-05,
|
| 1024 |
+
"loss": 0.2785,
|
| 1025 |
+
"step": 9000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 17.408123791102515,
|
| 1029 |
+
"eval_cer": 0.19269636564744075,
|
| 1030 |
+
"eval_loss": 0.4045611321926117,
|
| 1031 |
+
"eval_runtime": 235.9629,
|
| 1032 |
+
"eval_samples_per_second": 23.135,
|
| 1033 |
+
"eval_steps_per_second": 2.895,
|
| 1034 |
+
"eval_wer": 0.9981681626671551,
|
| 1035 |
+
"step": 9000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.60154738878143,
|
| 1039 |
+
"eval_cer": 0.19476814864786196,
|
| 1040 |
+
"eval_loss": 0.40159401297569275,
|
| 1041 |
+
"eval_runtime": 235.3013,
|
| 1042 |
+
"eval_samples_per_second": 23.2,
|
| 1043 |
+
"eval_steps_per_second": 2.903,
|
| 1044 |
+
"eval_wer": 0.9989008976002931,
|
| 1045 |
+
"step": 9100
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 17.79497098646035,
|
| 1049 |
+
"eval_cer": 0.19216557826716754,
|
| 1050 |
+
"eval_loss": 0.40133848786354065,
|
| 1051 |
+
"eval_runtime": 232.8231,
|
| 1052 |
+
"eval_samples_per_second": 23.447,
|
| 1053 |
+
"eval_steps_per_second": 2.934,
|
| 1054 |
+
"eval_wer": 0.9983513464004397,
|
| 1055 |
+
"step": 9200
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 17.988394584139265,
|
| 1059 |
+
"eval_cer": 0.19296004712022163,
|
| 1060 |
+
"eval_loss": 0.3879222273826599,
|
| 1061 |
+
"eval_runtime": 258.2005,
|
| 1062 |
+
"eval_samples_per_second": 21.142,
|
| 1063 |
+
"eval_steps_per_second": 2.645,
|
| 1064 |
+
"eval_wer": 0.9989008976002931,
|
| 1065 |
+
"step": 9300
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 18.181818181818183,
|
| 1069 |
+
"eval_cer": 0.19279224981936108,
|
| 1070 |
+
"eval_loss": 0.40087568759918213,
|
| 1071 |
+
"eval_runtime": 233.7931,
|
| 1072 |
+
"eval_samples_per_second": 23.35,
|
| 1073 |
+
"eval_steps_per_second": 2.921,
|
| 1074 |
+
"eval_wer": 0.9979849789338707,
|
| 1075 |
+
"step": 9400
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 18.3752417794971,
|
| 1079 |
+
"grad_norm": 2.837678909301758,
|
| 1080 |
+
"learning_rate": 2.27904e-05,
|
| 1081 |
+
"loss": 0.2647,
|
| 1082 |
+
"step": 9500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 18.3752417794971,
|
| 1086 |
+
"eval_cer": 0.19262787695321196,
|
| 1087 |
+
"eval_loss": 0.39038729667663574,
|
| 1088 |
+
"eval_runtime": 234.0768,
|
| 1089 |
+
"eval_samples_per_second": 23.321,
|
| 1090 |
+
"eval_steps_per_second": 2.918,
|
| 1091 |
+
"eval_wer": 0.9985345301337242,
|
| 1092 |
+
"step": 9500
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 18.568665377176014,
|
| 1096 |
+
"eval_cer": 0.19593930531917444,
|
| 1097 |
+
"eval_loss": 0.3944104015827179,
|
| 1098 |
+
"eval_runtime": 237.4314,
|
| 1099 |
+
"eval_samples_per_second": 22.992,
|
| 1100 |
+
"eval_steps_per_second": 2.877,
|
| 1101 |
+
"eval_wer": 0.9983513464004397,
|
| 1102 |
+
"step": 9600
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 18.762088974854933,
|
| 1106 |
+
"eval_cer": 0.19592218314561724,
|
| 1107 |
+
"eval_loss": 0.39569512009620667,
|
| 1108 |
+
"eval_runtime": 246.3149,
|
| 1109 |
+
"eval_samples_per_second": 22.163,
|
| 1110 |
+
"eval_steps_per_second": 2.773,
|
| 1111 |
+
"eval_wer": 0.9989008976002931,
|
| 1112 |
+
"step": 9700
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 18.95551257253385,
|
| 1116 |
+
"eval_cer": 0.1937613648426986,
|
| 1117 |
+
"eval_loss": 0.39492446184158325,
|
| 1118 |
+
"eval_runtime": 243.7942,
|
| 1119 |
+
"eval_samples_per_second": 22.392,
|
| 1120 |
+
"eval_steps_per_second": 2.802,
|
| 1121 |
+
"eval_wer": 0.9981681626671551,
|
| 1122 |
+
"step": 9800
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 19.148936170212767,
|
| 1126 |
+
"eval_cer": 0.1932579729401169,
|
| 1127 |
+
"eval_loss": 0.40386101603507996,
|
| 1128 |
+
"eval_runtime": 249.0686,
|
| 1129 |
+
"eval_samples_per_second": 21.918,
|
| 1130 |
+
"eval_steps_per_second": 2.742,
|
| 1131 |
+
"eval_wer": 0.9972522440007328,
|
| 1132 |
+
"step": 9900
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 19.342359767891683,
|
| 1136 |
+
"grad_norm": 3.1278374195098877,
|
| 1137 |
+
"learning_rate": 2.39904e-05,
|
| 1138 |
+
"loss": 0.248,
|
| 1139 |
+
"step": 10000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 19.342359767891683,
|
| 1143 |
+
"eval_cer": 0.19337097928559444,
|
| 1144 |
+
"eval_loss": 0.40820688009262085,
|
| 1145 |
+
"eval_runtime": 231.3525,
|
| 1146 |
+
"eval_samples_per_second": 23.596,
|
| 1147 |
+
"eval_steps_per_second": 2.952,
|
| 1148 |
+
"eval_wer": 0.9990840813335776,
|
| 1149 |
+
"step": 10000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.535783365570598,
|
| 1153 |
+
"eval_cer": 0.19222379365726203,
|
| 1154 |
+
"eval_loss": 0.4074006974697113,
|
| 1155 |
+
"eval_runtime": 253.2468,
|
| 1156 |
+
"eval_samples_per_second": 21.556,
|
| 1157 |
+
"eval_steps_per_second": 2.697,
|
| 1158 |
+
"eval_wer": 0.999267265066862,
|
| 1159 |
+
"step": 10100
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 19.729206963249517,
|
| 1163 |
+
"eval_cer": 0.19064170482057674,
|
| 1164 |
+
"eval_loss": 0.39546000957489014,
|
| 1165 |
+
"eval_runtime": 235.3118,
|
| 1166 |
+
"eval_samples_per_second": 23.199,
|
| 1167 |
+
"eval_steps_per_second": 2.903,
|
| 1168 |
+
"eval_wer": 0.9989008976002931,
|
| 1169 |
+
"step": 10200
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 19.922630560928432,
|
| 1173 |
+
"eval_cer": 0.19093620620576057,
|
| 1174 |
+
"eval_loss": 0.38558459281921387,
|
| 1175 |
+
"eval_runtime": 246.5841,
|
| 1176 |
+
"eval_samples_per_second": 22.138,
|
| 1177 |
+
"eval_steps_per_second": 2.77,
|
| 1178 |
+
"eval_wer": 0.9979849789338707,
|
| 1179 |
+
"step": 10300
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 20.0,
|
| 1183 |
+
"step": 10340,
|
| 1184 |
+
"total_flos": 1.4614133359859188e+19,
|
| 1185 |
+
"train_loss": 1.9748668191050192,
|
| 1186 |
+
"train_runtime": 66473.8913,
|
| 1187 |
+
"train_samples_per_second": 4.974,
|
| 1188 |
+
"train_steps_per_second": 0.156
|
| 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": 1.4614133359859188e+19,
|
| 1209 |
+
"train_batch_size": 16,
|
| 1210 |
+
"trial_name": null,
|
| 1211 |
+
"trial_params": null
|
| 1212 |
+
}
|