End of training
Browse files- README.md +8 -7
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jan23_15-53-35_ip-172-31-23-125/events.out.tfevents.1706038421.ip-172-31-23-125.44123.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1275 -0
README.md
CHANGED
@@ -2,20 +2,21 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: qanastek/whisper-base-french-cased
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
- fleurs
|
8 |
metrics:
|
9 |
- wer
|
10 |
model-index:
|
11 |
-
- name:
|
12 |
results:
|
13 |
- task:
|
14 |
name: Automatic Speech Recognition
|
15 |
type: automatic-speech-recognition
|
16 |
dataset:
|
17 |
-
name: fleurs
|
18 |
-
type: fleurs
|
19 |
config: fr_fr
|
20 |
split: test
|
21 |
args: fr_fr
|
@@ -28,11 +29,11 @@ model-index:
|
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
-
#
|
32 |
|
33 |
-
This model is a fine-tuned version of [qanastek/whisper-base-french-cased](https://huggingface.co/qanastek/whisper-base-french-cased) on the fleurs dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
- Wer: 23.7955
|
37 |
|
38 |
## Model description
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: qanastek/whisper-base-french-cased
|
4 |
tags:
|
5 |
+
- whisper-event
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
+
- google/fleurs
|
9 |
metrics:
|
10 |
- wer
|
11 |
model-index:
|
12 |
+
- name: Whisper Base French
|
13 |
results:
|
14 |
- task:
|
15 |
name: Automatic Speech Recognition
|
16 |
type: automatic-speech-recognition
|
17 |
dataset:
|
18 |
+
name: google/fleurs fr_fr
|
19 |
+
type: google/fleurs
|
20 |
config: fr_fr
|
21 |
split: test
|
22 |
args: fr_fr
|
|
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
should probably proofread and complete it, then remove this comment. -->
|
31 |
|
32 |
+
# Whisper Base French
|
33 |
|
34 |
+
This model is a fine-tuned version of [qanastek/whisper-base-french-cased](https://huggingface.co/qanastek/whisper-base-french-cased) on the google/fleurs fr_fr dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.5402
|
37 |
- Wer: 23.7955
|
38 |
|
39 |
## Model description
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 526.32,
|
3 |
+
"eval_loss": 0.5402421951293945,
|
4 |
+
"eval_runtime": 143.5733,
|
5 |
+
"eval_samples_per_second": 4.708,
|
6 |
+
"eval_steps_per_second": 0.153,
|
7 |
+
"eval_wer": 23.795498749652683,
|
8 |
+
"train_loss": 0.31816294193267824,
|
9 |
+
"train_runtime": 12909.7746,
|
10 |
+
"train_samples_per_second": 24.787,
|
11 |
+
"train_steps_per_second": 0.387
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 526.32,
|
3 |
+
"eval_loss": 0.5402421951293945,
|
4 |
+
"eval_runtime": 143.5733,
|
5 |
+
"eval_samples_per_second": 4.708,
|
6 |
+
"eval_steps_per_second": 0.153,
|
7 |
+
"eval_wer": 23.795498749652683
|
8 |
+
}
|
runs/Jan23_15-53-35_ip-172-31-23-125/events.out.tfevents.1706038421.ip-172-31-23-125.44123.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8b09084c9719e1ea7d93e9b6920be73482ec9821dd7e89efd9ee4ca86e4ac0f
|
3 |
+
size 406
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 526.32,
|
3 |
+
"train_loss": 0.31816294193267824,
|
4 |
+
"train_runtime": 12909.7746,
|
5 |
+
"train_samples_per_second": 24.787,
|
6 |
+
"train_steps_per_second": 0.387
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1275 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 23.795498749652683,
|
3 |
+
"best_model_checkpoint": "./checkpoint-4000",
|
4 |
+
"epoch": 526.3157894736842,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 5000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.63,
|
13 |
+
"learning_rate": 4.4e-09,
|
14 |
+
"loss": 0.8459,
|
15 |
+
"step": 25
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 5.26,
|
19 |
+
"learning_rate": 9.4e-09,
|
20 |
+
"loss": 0.8681,
|
21 |
+
"step": 50
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 7.89,
|
25 |
+
"learning_rate": 1.4399999999999998e-08,
|
26 |
+
"loss": 0.8349,
|
27 |
+
"step": 75
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 10.53,
|
31 |
+
"learning_rate": 1.94e-08,
|
32 |
+
"loss": 0.8471,
|
33 |
+
"step": 100
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 13.16,
|
37 |
+
"learning_rate": 2.4399999999999997e-08,
|
38 |
+
"loss": 0.8299,
|
39 |
+
"step": 125
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 15.79,
|
43 |
+
"learning_rate": 2.94e-08,
|
44 |
+
"loss": 0.8228,
|
45 |
+
"step": 150
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 18.42,
|
49 |
+
"learning_rate": 3.44e-08,
|
50 |
+
"loss": 0.8015,
|
51 |
+
"step": 175
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 21.05,
|
55 |
+
"learning_rate": 3.94e-08,
|
56 |
+
"loss": 0.8041,
|
57 |
+
"step": 200
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 23.68,
|
61 |
+
"learning_rate": 4.44e-08,
|
62 |
+
"loss": 0.797,
|
63 |
+
"step": 225
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 26.32,
|
67 |
+
"learning_rate": 4.94e-08,
|
68 |
+
"loss": 0.7771,
|
69 |
+
"step": 250
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 28.95,
|
73 |
+
"learning_rate": 5.4400000000000004e-08,
|
74 |
+
"loss": 0.7623,
|
75 |
+
"step": 275
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 31.58,
|
79 |
+
"learning_rate": 5.9399999999999996e-08,
|
80 |
+
"loss": 0.7524,
|
81 |
+
"step": 300
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 34.21,
|
85 |
+
"learning_rate": 6.44e-08,
|
86 |
+
"loss": 0.7384,
|
87 |
+
"step": 325
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 36.84,
|
91 |
+
"learning_rate": 6.939999999999999e-08,
|
92 |
+
"loss": 0.715,
|
93 |
+
"step": 350
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 39.47,
|
97 |
+
"learning_rate": 7.439999999999999e-08,
|
98 |
+
"loss": 0.6994,
|
99 |
+
"step": 375
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 42.11,
|
103 |
+
"learning_rate": 7.94e-08,
|
104 |
+
"loss": 0.6721,
|
105 |
+
"step": 400
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 44.74,
|
109 |
+
"learning_rate": 8.439999999999999e-08,
|
110 |
+
"loss": 0.676,
|
111 |
+
"step": 425
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 47.37,
|
115 |
+
"learning_rate": 8.939999999999999e-08,
|
116 |
+
"loss": 0.6614,
|
117 |
+
"step": 450
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 50.0,
|
121 |
+
"learning_rate": 9.439999999999999e-08,
|
122 |
+
"loss": 0.625,
|
123 |
+
"step": 475
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 52.63,
|
127 |
+
"learning_rate": 9.939999999999999e-08,
|
128 |
+
"loss": 0.5845,
|
129 |
+
"step": 500
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 55.26,
|
133 |
+
"learning_rate": 9.95111111111111e-08,
|
134 |
+
"loss": 0.5787,
|
135 |
+
"step": 525
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 57.89,
|
139 |
+
"learning_rate": 9.895555555555555e-08,
|
140 |
+
"loss": 0.5624,
|
141 |
+
"step": 550
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 60.53,
|
145 |
+
"learning_rate": 9.84e-08,
|
146 |
+
"loss": 0.5237,
|
147 |
+
"step": 575
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 63.16,
|
151 |
+
"learning_rate": 9.784444444444444e-08,
|
152 |
+
"loss": 0.5334,
|
153 |
+
"step": 600
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 65.79,
|
157 |
+
"learning_rate": 9.728888888888889e-08,
|
158 |
+
"loss": 0.5064,
|
159 |
+
"step": 625
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 68.42,
|
163 |
+
"learning_rate": 9.673333333333334e-08,
|
164 |
+
"loss": 0.5078,
|
165 |
+
"step": 650
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 71.05,
|
169 |
+
"learning_rate": 9.617777777777777e-08,
|
170 |
+
"loss": 0.485,
|
171 |
+
"step": 675
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 73.68,
|
175 |
+
"learning_rate": 9.562222222222221e-08,
|
176 |
+
"loss": 0.4678,
|
177 |
+
"step": 700
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 76.32,
|
181 |
+
"learning_rate": 9.506666666666666e-08,
|
182 |
+
"loss": 0.4636,
|
183 |
+
"step": 725
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 78.95,
|
187 |
+
"learning_rate": 9.45111111111111e-08,
|
188 |
+
"loss": 0.4707,
|
189 |
+
"step": 750
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 81.58,
|
193 |
+
"learning_rate": 9.395555555555555e-08,
|
194 |
+
"loss": 0.4725,
|
195 |
+
"step": 775
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 84.21,
|
199 |
+
"learning_rate": 9.34e-08,
|
200 |
+
"loss": 0.4595,
|
201 |
+
"step": 800
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 86.84,
|
205 |
+
"learning_rate": 9.284444444444444e-08,
|
206 |
+
"loss": 0.4449,
|
207 |
+
"step": 825
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 89.47,
|
211 |
+
"learning_rate": 9.228888888888889e-08,
|
212 |
+
"loss": 0.4254,
|
213 |
+
"step": 850
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 92.11,
|
217 |
+
"learning_rate": 9.173333333333333e-08,
|
218 |
+
"loss": 0.4222,
|
219 |
+
"step": 875
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 94.74,
|
223 |
+
"learning_rate": 9.117777777777777e-08,
|
224 |
+
"loss": 0.4247,
|
225 |
+
"step": 900
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 97.37,
|
229 |
+
"learning_rate": 9.062222222222222e-08,
|
230 |
+
"loss": 0.4306,
|
231 |
+
"step": 925
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 100.0,
|
235 |
+
"learning_rate": 9.006666666666665e-08,
|
236 |
+
"loss": 0.4017,
|
237 |
+
"step": 950
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 102.63,
|
241 |
+
"learning_rate": 8.95111111111111e-08,
|
242 |
+
"loss": 0.4176,
|
243 |
+
"step": 975
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 105.26,
|
247 |
+
"learning_rate": 8.895555555555555e-08,
|
248 |
+
"loss": 0.3835,
|
249 |
+
"step": 1000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 105.26,
|
253 |
+
"eval_loss": 0.5891541838645935,
|
254 |
+
"eval_runtime": 160.0944,
|
255 |
+
"eval_samples_per_second": 4.223,
|
256 |
+
"eval_steps_per_second": 0.137,
|
257 |
+
"eval_wer": 25.423728813559322,
|
258 |
+
"step": 1000
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 107.89,
|
262 |
+
"learning_rate": 8.84e-08,
|
263 |
+
"loss": 0.4049,
|
264 |
+
"step": 1025
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 110.53,
|
268 |
+
"learning_rate": 8.784444444444445e-08,
|
269 |
+
"loss": 0.396,
|
270 |
+
"step": 1050
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 113.16,
|
274 |
+
"learning_rate": 8.72888888888889e-08,
|
275 |
+
"loss": 0.3819,
|
276 |
+
"step": 1075
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 115.79,
|
280 |
+
"learning_rate": 8.673333333333333e-08,
|
281 |
+
"loss": 0.3813,
|
282 |
+
"step": 1100
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 118.42,
|
286 |
+
"learning_rate": 8.617777777777778e-08,
|
287 |
+
"loss": 0.3786,
|
288 |
+
"step": 1125
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 121.05,
|
292 |
+
"learning_rate": 8.562222222222221e-08,
|
293 |
+
"loss": 0.3623,
|
294 |
+
"step": 1150
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 123.68,
|
298 |
+
"learning_rate": 8.506666666666666e-08,
|
299 |
+
"loss": 0.3702,
|
300 |
+
"step": 1175
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 126.32,
|
304 |
+
"learning_rate": 8.451111111111111e-08,
|
305 |
+
"loss": 0.3578,
|
306 |
+
"step": 1200
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 128.95,
|
310 |
+
"learning_rate": 8.395555555555556e-08,
|
311 |
+
"loss": 0.3559,
|
312 |
+
"step": 1225
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 131.58,
|
316 |
+
"learning_rate": 8.339999999999999e-08,
|
317 |
+
"loss": 0.3548,
|
318 |
+
"step": 1250
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 134.21,
|
322 |
+
"learning_rate": 8.284444444444444e-08,
|
323 |
+
"loss": 0.345,
|
324 |
+
"step": 1275
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 136.84,
|
328 |
+
"learning_rate": 8.228888888888889e-08,
|
329 |
+
"loss": 0.3574,
|
330 |
+
"step": 1300
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 139.47,
|
334 |
+
"learning_rate": 8.173333333333334e-08,
|
335 |
+
"loss": 0.3467,
|
336 |
+
"step": 1325
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 142.11,
|
340 |
+
"learning_rate": 8.117777777777777e-08,
|
341 |
+
"loss": 0.3511,
|
342 |
+
"step": 1350
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 144.74,
|
346 |
+
"learning_rate": 8.062222222222221e-08,
|
347 |
+
"loss": 0.3376,
|
348 |
+
"step": 1375
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 147.37,
|
352 |
+
"learning_rate": 8.006666666666666e-08,
|
353 |
+
"loss": 0.3369,
|
354 |
+
"step": 1400
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 150.0,
|
358 |
+
"learning_rate": 7.95111111111111e-08,
|
359 |
+
"loss": 0.3302,
|
360 |
+
"step": 1425
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 152.63,
|
364 |
+
"learning_rate": 7.895555555555555e-08,
|
365 |
+
"loss": 0.3339,
|
366 |
+
"step": 1450
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 155.26,
|
370 |
+
"learning_rate": 7.84e-08,
|
371 |
+
"loss": 0.33,
|
372 |
+
"step": 1475
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 157.89,
|
376 |
+
"learning_rate": 7.784444444444445e-08,
|
377 |
+
"loss": 0.3285,
|
378 |
+
"step": 1500
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 160.53,
|
382 |
+
"learning_rate": 7.728888888888888e-08,
|
383 |
+
"loss": 0.3236,
|
384 |
+
"step": 1525
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 163.16,
|
388 |
+
"learning_rate": 7.673333333333333e-08,
|
389 |
+
"loss": 0.3167,
|
390 |
+
"step": 1550
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 165.79,
|
394 |
+
"learning_rate": 7.617777777777778e-08,
|
395 |
+
"loss": 0.3117,
|
396 |
+
"step": 1575
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 168.42,
|
400 |
+
"learning_rate": 7.562222222222222e-08,
|
401 |
+
"loss": 0.3191,
|
402 |
+
"step": 1600
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 171.05,
|
406 |
+
"learning_rate": 7.506666666666666e-08,
|
407 |
+
"loss": 0.3058,
|
408 |
+
"step": 1625
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 173.68,
|
412 |
+
"learning_rate": 7.45111111111111e-08,
|
413 |
+
"loss": 0.3177,
|
414 |
+
"step": 1650
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 176.32,
|
418 |
+
"learning_rate": 7.395555555555555e-08,
|
419 |
+
"loss": 0.3017,
|
420 |
+
"step": 1675
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 178.95,
|
424 |
+
"learning_rate": 7.34e-08,
|
425 |
+
"loss": 0.3059,
|
426 |
+
"step": 1700
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 181.58,
|
430 |
+
"learning_rate": 7.284444444444444e-08,
|
431 |
+
"loss": 0.3124,
|
432 |
+
"step": 1725
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 184.21,
|
436 |
+
"learning_rate": 7.228888888888889e-08,
|
437 |
+
"loss": 0.2987,
|
438 |
+
"step": 1750
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 186.84,
|
442 |
+
"learning_rate": 7.173333333333334e-08,
|
443 |
+
"loss": 0.2981,
|
444 |
+
"step": 1775
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 189.47,
|
448 |
+
"learning_rate": 7.117777777777778e-08,
|
449 |
+
"loss": 0.3084,
|
450 |
+
"step": 1800
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 192.11,
|
454 |
+
"learning_rate": 7.062222222222221e-08,
|
455 |
+
"loss": 0.2858,
|
456 |
+
"step": 1825
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 194.74,
|
460 |
+
"learning_rate": 7.006666666666666e-08,
|
461 |
+
"loss": 0.2978,
|
462 |
+
"step": 1850
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 197.37,
|
466 |
+
"learning_rate": 6.951111111111111e-08,
|
467 |
+
"loss": 0.2818,
|
468 |
+
"step": 1875
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 200.0,
|
472 |
+
"learning_rate": 6.895555555555556e-08,
|
473 |
+
"loss": 0.2902,
|
474 |
+
"step": 1900
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 202.63,
|
478 |
+
"learning_rate": 6.84e-08,
|
479 |
+
"loss": 0.2838,
|
480 |
+
"step": 1925
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 205.26,
|
484 |
+
"learning_rate": 6.784444444444444e-08,
|
485 |
+
"loss": 0.2992,
|
486 |
+
"step": 1950
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 207.89,
|
490 |
+
"learning_rate": 6.728888888888889e-08,
|
491 |
+
"loss": 0.2774,
|
492 |
+
"step": 1975
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 210.53,
|
496 |
+
"learning_rate": 6.673333333333334e-08,
|
497 |
+
"loss": 0.2837,
|
498 |
+
"step": 2000
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 210.53,
|
502 |
+
"eval_loss": 0.5525617003440857,
|
503 |
+
"eval_runtime": 144.9276,
|
504 |
+
"eval_samples_per_second": 4.664,
|
505 |
+
"eval_steps_per_second": 0.152,
|
506 |
+
"eval_wer": 23.895526535148655,
|
507 |
+
"step": 2000
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 213.16,
|
511 |
+
"learning_rate": 6.617777777777777e-08,
|
512 |
+
"loss": 0.2805,
|
513 |
+
"step": 2025
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 215.79,
|
517 |
+
"learning_rate": 6.562222222222222e-08,
|
518 |
+
"loss": 0.2759,
|
519 |
+
"step": 2050
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 218.42,
|
523 |
+
"learning_rate": 6.506666666666665e-08,
|
524 |
+
"loss": 0.2667,
|
525 |
+
"step": 2075
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 221.05,
|
529 |
+
"learning_rate": 6.45111111111111e-08,
|
530 |
+
"loss": 0.2777,
|
531 |
+
"step": 2100
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 223.68,
|
535 |
+
"learning_rate": 6.395555555555555e-08,
|
536 |
+
"loss": 0.2672,
|
537 |
+
"step": 2125
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 226.32,
|
541 |
+
"learning_rate": 6.34e-08,
|
542 |
+
"loss": 0.2739,
|
543 |
+
"step": 2150
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 228.95,
|
547 |
+
"learning_rate": 6.284444444444445e-08,
|
548 |
+
"loss": 0.2819,
|
549 |
+
"step": 2175
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 231.58,
|
553 |
+
"learning_rate": 6.22888888888889e-08,
|
554 |
+
"loss": 0.2646,
|
555 |
+
"step": 2200
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 234.21,
|
559 |
+
"learning_rate": 6.173333333333333e-08,
|
560 |
+
"loss": 0.2618,
|
561 |
+
"step": 2225
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 236.84,
|
565 |
+
"learning_rate": 6.117777777777778e-08,
|
566 |
+
"loss": 0.2711,
|
567 |
+
"step": 2250
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 239.47,
|
571 |
+
"learning_rate": 6.062222222222221e-08,
|
572 |
+
"loss": 0.2644,
|
573 |
+
"step": 2275
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 242.11,
|
577 |
+
"learning_rate": 6.006666666666666e-08,
|
578 |
+
"loss": 0.2494,
|
579 |
+
"step": 2300
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 244.74,
|
583 |
+
"learning_rate": 5.951111111111111e-08,
|
584 |
+
"loss": 0.2601,
|
585 |
+
"step": 2325
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 247.37,
|
589 |
+
"learning_rate": 5.895555555555556e-08,
|
590 |
+
"loss": 0.2538,
|
591 |
+
"step": 2350
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 250.0,
|
595 |
+
"learning_rate": 5.8399999999999994e-08,
|
596 |
+
"loss": 0.2551,
|
597 |
+
"step": 2375
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 252.63,
|
601 |
+
"learning_rate": 5.784444444444444e-08,
|
602 |
+
"loss": 0.2494,
|
603 |
+
"step": 2400
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 255.26,
|
607 |
+
"learning_rate": 5.7288888888888884e-08,
|
608 |
+
"loss": 0.2518,
|
609 |
+
"step": 2425
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 257.89,
|
613 |
+
"learning_rate": 5.673333333333333e-08,
|
614 |
+
"loss": 0.2455,
|
615 |
+
"step": 2450
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 260.53,
|
619 |
+
"learning_rate": 5.617777777777778e-08,
|
620 |
+
"loss": 0.2606,
|
621 |
+
"step": 2475
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 263.16,
|
625 |
+
"learning_rate": 5.5622222222222215e-08,
|
626 |
+
"loss": 0.2533,
|
627 |
+
"step": 2500
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 265.79,
|
631 |
+
"learning_rate": 5.5066666666666663e-08,
|
632 |
+
"loss": 0.2436,
|
633 |
+
"step": 2525
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 268.42,
|
637 |
+
"learning_rate": 5.4511111111111105e-08,
|
638 |
+
"loss": 0.2346,
|
639 |
+
"step": 2550
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 271.05,
|
643 |
+
"learning_rate": 5.3955555555555553e-08,
|
644 |
+
"loss": 0.2456,
|
645 |
+
"step": 2575
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 273.68,
|
649 |
+
"learning_rate": 5.34e-08,
|
650 |
+
"loss": 0.2462,
|
651 |
+
"step": 2600
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 276.32,
|
655 |
+
"learning_rate": 5.284444444444445e-08,
|
656 |
+
"loss": 0.24,
|
657 |
+
"step": 2625
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 278.95,
|
661 |
+
"learning_rate": 5.2288888888888885e-08,
|
662 |
+
"loss": 0.2466,
|
663 |
+
"step": 2650
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 281.58,
|
667 |
+
"learning_rate": 5.173333333333333e-08,
|
668 |
+
"loss": 0.24,
|
669 |
+
"step": 2675
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 284.21,
|
673 |
+
"learning_rate": 5.1177777777777775e-08,
|
674 |
+
"loss": 0.2419,
|
675 |
+
"step": 2700
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 286.84,
|
679 |
+
"learning_rate": 5.0622222222222223e-08,
|
680 |
+
"loss": 0.2366,
|
681 |
+
"step": 2725
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 289.47,
|
685 |
+
"learning_rate": 5.0066666666666665e-08,
|
686 |
+
"loss": 0.232,
|
687 |
+
"step": 2750
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 292.11,
|
691 |
+
"learning_rate": 4.9511111111111107e-08,
|
692 |
+
"loss": 0.235,
|
693 |
+
"step": 2775
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 294.74,
|
697 |
+
"learning_rate": 4.8955555555555555e-08,
|
698 |
+
"loss": 0.234,
|
699 |
+
"step": 2800
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 297.37,
|
703 |
+
"learning_rate": 4.8399999999999997e-08,
|
704 |
+
"loss": 0.2368,
|
705 |
+
"step": 2825
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 300.0,
|
709 |
+
"learning_rate": 4.7844444444444445e-08,
|
710 |
+
"loss": 0.2231,
|
711 |
+
"step": 2850
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 302.63,
|
715 |
+
"learning_rate": 4.7288888888888887e-08,
|
716 |
+
"loss": 0.224,
|
717 |
+
"step": 2875
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 305.26,
|
721 |
+
"learning_rate": 4.673333333333333e-08,
|
722 |
+
"loss": 0.2285,
|
723 |
+
"step": 2900
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 307.89,
|
727 |
+
"learning_rate": 4.6177777777777777e-08,
|
728 |
+
"loss": 0.2265,
|
729 |
+
"step": 2925
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 310.53,
|
733 |
+
"learning_rate": 4.562222222222222e-08,
|
734 |
+
"loss": 0.2238,
|
735 |
+
"step": 2950
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 313.16,
|
739 |
+
"learning_rate": 4.5066666666666667e-08,
|
740 |
+
"loss": 0.2224,
|
741 |
+
"step": 2975
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 315.79,
|
745 |
+
"learning_rate": 4.451111111111111e-08,
|
746 |
+
"loss": 0.2323,
|
747 |
+
"step": 3000
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 315.79,
|
751 |
+
"eval_loss": 0.5431821942329407,
|
752 |
+
"eval_runtime": 144.0249,
|
753 |
+
"eval_samples_per_second": 4.694,
|
754 |
+
"eval_steps_per_second": 0.153,
|
755 |
+
"eval_wer": 24.012225618227284,
|
756 |
+
"step": 3000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 318.42,
|
760 |
+
"learning_rate": 4.395555555555555e-08,
|
761 |
+
"loss": 0.2231,
|
762 |
+
"step": 3025
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 321.05,
|
766 |
+
"learning_rate": 4.34e-08,
|
767 |
+
"loss": 0.2132,
|
768 |
+
"step": 3050
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 323.68,
|
772 |
+
"learning_rate": 4.2844444444444446e-08,
|
773 |
+
"loss": 0.2275,
|
774 |
+
"step": 3075
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 326.32,
|
778 |
+
"learning_rate": 4.228888888888889e-08,
|
779 |
+
"loss": 0.2149,
|
780 |
+
"step": 3100
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 328.95,
|
784 |
+
"learning_rate": 4.173333333333333e-08,
|
785 |
+
"loss": 0.214,
|
786 |
+
"step": 3125
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 331.58,
|
790 |
+
"learning_rate": 4.117777777777778e-08,
|
791 |
+
"loss": 0.2181,
|
792 |
+
"step": 3150
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 334.21,
|
796 |
+
"learning_rate": 4.062222222222222e-08,
|
797 |
+
"loss": 0.2153,
|
798 |
+
"step": 3175
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 336.84,
|
802 |
+
"learning_rate": 4.006666666666667e-08,
|
803 |
+
"loss": 0.2266,
|
804 |
+
"step": 3200
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 339.47,
|
808 |
+
"learning_rate": 3.951111111111111e-08,
|
809 |
+
"loss": 0.2154,
|
810 |
+
"step": 3225
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 342.11,
|
814 |
+
"learning_rate": 3.895555555555555e-08,
|
815 |
+
"loss": 0.2088,
|
816 |
+
"step": 3250
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 344.74,
|
820 |
+
"learning_rate": 3.84e-08,
|
821 |
+
"loss": 0.2104,
|
822 |
+
"step": 3275
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 347.37,
|
826 |
+
"learning_rate": 3.784444444444445e-08,
|
827 |
+
"loss": 0.2115,
|
828 |
+
"step": 3300
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 350.0,
|
832 |
+
"learning_rate": 3.728888888888888e-08,
|
833 |
+
"loss": 0.2103,
|
834 |
+
"step": 3325
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 352.63,
|
838 |
+
"learning_rate": 3.673333333333333e-08,
|
839 |
+
"loss": 0.209,
|
840 |
+
"step": 3350
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 355.26,
|
844 |
+
"learning_rate": 3.617777777777777e-08,
|
845 |
+
"loss": 0.216,
|
846 |
+
"step": 3375
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 357.89,
|
850 |
+
"learning_rate": 3.562222222222222e-08,
|
851 |
+
"loss": 0.2125,
|
852 |
+
"step": 3400
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 360.53,
|
856 |
+
"learning_rate": 3.506666666666667e-08,
|
857 |
+
"loss": 0.2161,
|
858 |
+
"step": 3425
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 363.16,
|
862 |
+
"learning_rate": 3.4511111111111105e-08,
|
863 |
+
"loss": 0.2148,
|
864 |
+
"step": 3450
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 365.79,
|
868 |
+
"learning_rate": 3.395555555555555e-08,
|
869 |
+
"loss": 0.2093,
|
870 |
+
"step": 3475
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 368.42,
|
874 |
+
"learning_rate": 3.34e-08,
|
875 |
+
"loss": 0.215,
|
876 |
+
"step": 3500
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 371.05,
|
880 |
+
"learning_rate": 3.284444444444444e-08,
|
881 |
+
"loss": 0.2142,
|
882 |
+
"step": 3525
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 373.68,
|
886 |
+
"learning_rate": 3.2288888888888885e-08,
|
887 |
+
"loss": 0.2069,
|
888 |
+
"step": 3550
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 376.32,
|
892 |
+
"learning_rate": 3.173333333333333e-08,
|
893 |
+
"loss": 0.2067,
|
894 |
+
"step": 3575
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 378.95,
|
898 |
+
"learning_rate": 3.1177777777777775e-08,
|
899 |
+
"loss": 0.2084,
|
900 |
+
"step": 3600
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 381.58,
|
904 |
+
"learning_rate": 3.062222222222222e-08,
|
905 |
+
"loss": 0.209,
|
906 |
+
"step": 3625
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 384.21,
|
910 |
+
"learning_rate": 3.006666666666667e-08,
|
911 |
+
"loss": 0.2139,
|
912 |
+
"step": 3650
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 386.84,
|
916 |
+
"learning_rate": 2.951111111111111e-08,
|
917 |
+
"loss": 0.2019,
|
918 |
+
"step": 3675
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 389.47,
|
922 |
+
"learning_rate": 2.8955555555555555e-08,
|
923 |
+
"loss": 0.1983,
|
924 |
+
"step": 3700
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 392.11,
|
928 |
+
"learning_rate": 2.8399999999999996e-08,
|
929 |
+
"loss": 0.2043,
|
930 |
+
"step": 3725
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 394.74,
|
934 |
+
"learning_rate": 2.784444444444444e-08,
|
935 |
+
"loss": 0.2044,
|
936 |
+
"step": 3750
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 397.37,
|
940 |
+
"learning_rate": 2.728888888888889e-08,
|
941 |
+
"loss": 0.2025,
|
942 |
+
"step": 3775
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 400.0,
|
946 |
+
"learning_rate": 2.673333333333333e-08,
|
947 |
+
"loss": 0.2036,
|
948 |
+
"step": 3800
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 402.63,
|
952 |
+
"learning_rate": 2.6177777777777776e-08,
|
953 |
+
"loss": 0.1942,
|
954 |
+
"step": 3825
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 405.26,
|
958 |
+
"learning_rate": 2.5622222222222224e-08,
|
959 |
+
"loss": 0.1977,
|
960 |
+
"step": 3850
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 407.89,
|
964 |
+
"learning_rate": 2.5066666666666663e-08,
|
965 |
+
"loss": 0.2042,
|
966 |
+
"step": 3875
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 410.53,
|
970 |
+
"learning_rate": 2.451111111111111e-08,
|
971 |
+
"loss": 0.1933,
|
972 |
+
"step": 3900
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 413.16,
|
976 |
+
"learning_rate": 2.3955555555555553e-08,
|
977 |
+
"loss": 0.1988,
|
978 |
+
"step": 3925
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 415.79,
|
982 |
+
"learning_rate": 2.34e-08,
|
983 |
+
"loss": 0.1943,
|
984 |
+
"step": 3950
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 418.42,
|
988 |
+
"learning_rate": 2.2844444444444443e-08,
|
989 |
+
"loss": 0.2033,
|
990 |
+
"step": 3975
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 421.05,
|
994 |
+
"learning_rate": 2.2288888888888888e-08,
|
995 |
+
"loss": 0.1961,
|
996 |
+
"step": 4000
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 421.05,
|
1000 |
+
"eval_loss": 0.5402421951293945,
|
1001 |
+
"eval_runtime": 143.5894,
|
1002 |
+
"eval_samples_per_second": 4.708,
|
1003 |
+
"eval_steps_per_second": 0.153,
|
1004 |
+
"eval_wer": 23.795498749652683,
|
1005 |
+
"step": 4000
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 423.68,
|
1009 |
+
"learning_rate": 2.1733333333333333e-08,
|
1010 |
+
"loss": 0.2009,
|
1011 |
+
"step": 4025
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 426.32,
|
1015 |
+
"learning_rate": 2.1177777777777778e-08,
|
1016 |
+
"loss": 0.1961,
|
1017 |
+
"step": 4050
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 428.95,
|
1021 |
+
"learning_rate": 2.0622222222222223e-08,
|
1022 |
+
"loss": 0.1987,
|
1023 |
+
"step": 4075
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 431.58,
|
1027 |
+
"learning_rate": 2.0066666666666664e-08,
|
1028 |
+
"loss": 0.1951,
|
1029 |
+
"step": 4100
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 434.21,
|
1033 |
+
"learning_rate": 1.9533333333333333e-08,
|
1034 |
+
"loss": 0.1914,
|
1035 |
+
"step": 4125
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 436.84,
|
1039 |
+
"learning_rate": 1.8977777777777775e-08,
|
1040 |
+
"loss": 0.1955,
|
1041 |
+
"step": 4150
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 439.47,
|
1045 |
+
"learning_rate": 1.8422222222222223e-08,
|
1046 |
+
"loss": 0.1967,
|
1047 |
+
"step": 4175
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 442.11,
|
1051 |
+
"learning_rate": 1.7866666666666665e-08,
|
1052 |
+
"loss": 0.2011,
|
1053 |
+
"step": 4200
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 444.74,
|
1057 |
+
"learning_rate": 1.731111111111111e-08,
|
1058 |
+
"loss": 0.1953,
|
1059 |
+
"step": 4225
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 447.37,
|
1063 |
+
"learning_rate": 1.6755555555555554e-08,
|
1064 |
+
"loss": 0.1927,
|
1065 |
+
"step": 4250
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 450.0,
|
1069 |
+
"learning_rate": 1.62e-08,
|
1070 |
+
"loss": 0.1918,
|
1071 |
+
"step": 4275
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 452.63,
|
1075 |
+
"learning_rate": 1.5644444444444444e-08,
|
1076 |
+
"loss": 0.195,
|
1077 |
+
"step": 4300
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 455.26,
|
1081 |
+
"learning_rate": 1.5088888888888886e-08,
|
1082 |
+
"loss": 0.1939,
|
1083 |
+
"step": 4325
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 457.89,
|
1087 |
+
"learning_rate": 1.4533333333333333e-08,
|
1088 |
+
"loss": 0.1916,
|
1089 |
+
"step": 4350
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 460.53,
|
1093 |
+
"learning_rate": 1.3977777777777778e-08,
|
1094 |
+
"loss": 0.1968,
|
1095 |
+
"step": 4375
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 463.16,
|
1099 |
+
"learning_rate": 1.3422222222222221e-08,
|
1100 |
+
"loss": 0.193,
|
1101 |
+
"step": 4400
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 465.79,
|
1105 |
+
"learning_rate": 1.2866666666666668e-08,
|
1106 |
+
"loss": 0.1888,
|
1107 |
+
"step": 4425
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 468.42,
|
1111 |
+
"learning_rate": 1.2311111111111111e-08,
|
1112 |
+
"loss": 0.1858,
|
1113 |
+
"step": 4450
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 471.05,
|
1117 |
+
"learning_rate": 1.1755555555555554e-08,
|
1118 |
+
"loss": 0.1872,
|
1119 |
+
"step": 4475
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 473.68,
|
1123 |
+
"learning_rate": 1.12e-08,
|
1124 |
+
"loss": 0.1919,
|
1125 |
+
"step": 4500
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 476.32,
|
1129 |
+
"learning_rate": 1.0644444444444443e-08,
|
1130 |
+
"loss": 0.1919,
|
1131 |
+
"step": 4525
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 478.95,
|
1135 |
+
"learning_rate": 1.0088888888888888e-08,
|
1136 |
+
"loss": 0.1901,
|
1137 |
+
"step": 4550
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 481.58,
|
1141 |
+
"learning_rate": 9.533333333333334e-09,
|
1142 |
+
"loss": 0.1947,
|
1143 |
+
"step": 4575
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 484.21,
|
1147 |
+
"learning_rate": 8.977777777777778e-09,
|
1148 |
+
"loss": 0.189,
|
1149 |
+
"step": 4600
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 486.84,
|
1153 |
+
"learning_rate": 8.422222222222223e-09,
|
1154 |
+
"loss": 0.1872,
|
1155 |
+
"step": 4625
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 489.47,
|
1159 |
+
"learning_rate": 7.866666666666666e-09,
|
1160 |
+
"loss": 0.1848,
|
1161 |
+
"step": 4650
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 492.11,
|
1165 |
+
"learning_rate": 7.311111111111111e-09,
|
1166 |
+
"loss": 0.1876,
|
1167 |
+
"step": 4675
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 494.74,
|
1171 |
+
"learning_rate": 6.755555555555554e-09,
|
1172 |
+
"loss": 0.1911,
|
1173 |
+
"step": 4700
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 497.37,
|
1177 |
+
"learning_rate": 6.199999999999999e-09,
|
1178 |
+
"loss": 0.1882,
|
1179 |
+
"step": 4725
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 500.0,
|
1183 |
+
"learning_rate": 5.644444444444444e-09,
|
1184 |
+
"loss": 0.1872,
|
1185 |
+
"step": 4750
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 502.63,
|
1189 |
+
"learning_rate": 5.088888888888888e-09,
|
1190 |
+
"loss": 0.1895,
|
1191 |
+
"step": 4775
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 505.26,
|
1195 |
+
"learning_rate": 4.533333333333333e-09,
|
1196 |
+
"loss": 0.1895,
|
1197 |
+
"step": 4800
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 507.89,
|
1201 |
+
"learning_rate": 3.9777777777777776e-09,
|
1202 |
+
"loss": 0.1834,
|
1203 |
+
"step": 4825
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 510.53,
|
1207 |
+
"learning_rate": 3.422222222222222e-09,
|
1208 |
+
"loss": 0.1923,
|
1209 |
+
"step": 4850
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 513.16,
|
1213 |
+
"learning_rate": 2.8666666666666667e-09,
|
1214 |
+
"loss": 0.1884,
|
1215 |
+
"step": 4875
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 515.79,
|
1219 |
+
"learning_rate": 2.311111111111111e-09,
|
1220 |
+
"loss": 0.1834,
|
1221 |
+
"step": 4900
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 518.42,
|
1225 |
+
"learning_rate": 1.7555555555555556e-09,
|
1226 |
+
"loss": 0.1964,
|
1227 |
+
"step": 4925
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 521.05,
|
1231 |
+
"learning_rate": 1.2e-09,
|
1232 |
+
"loss": 0.1923,
|
1233 |
+
"step": 4950
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 523.68,
|
1237 |
+
"learning_rate": 6.444444444444445e-10,
|
1238 |
+
"loss": 0.1866,
|
1239 |
+
"step": 4975
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 526.32,
|
1243 |
+
"learning_rate": 8.888888888888889e-11,
|
1244 |
+
"loss": 0.1863,
|
1245 |
+
"step": 5000
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 526.32,
|
1249 |
+
"eval_loss": 0.5395069122314453,
|
1250 |
+
"eval_runtime": 143.5193,
|
1251 |
+
"eval_samples_per_second": 4.71,
|
1252 |
+
"eval_steps_per_second": 0.153,
|
1253 |
+
"eval_wer": 23.795498749652683,
|
1254 |
+
"step": 5000
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 526.32,
|
1258 |
+
"step": 5000,
|
1259 |
+
"total_flos": 1.97317080317952e+19,
|
1260 |
+
"train_loss": 0.31816294193267824,
|
1261 |
+
"train_runtime": 12909.7746,
|
1262 |
+
"train_samples_per_second": 24.787,
|
1263 |
+
"train_steps_per_second": 0.387
|
1264 |
+
}
|
1265 |
+
],
|
1266 |
+
"logging_steps": 25,
|
1267 |
+
"max_steps": 5000,
|
1268 |
+
"num_input_tokens_seen": 0,
|
1269 |
+
"num_train_epochs": 556,
|
1270 |
+
"save_steps": 1000,
|
1271 |
+
"total_flos": 1.97317080317952e+19,
|
1272 |
+
"train_batch_size": 32,
|
1273 |
+
"trial_name": null,
|
1274 |
+
"trial_params": null
|
1275 |
+
}
|