End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/events.out.tfevents.1643155382.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.0 +2 -2
- runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/events.out.tfevents.1643225941.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +835 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 1.1176735162734985,
|
| 4 |
+
"eval_runtime": 25.4564,
|
| 5 |
+
"eval_samples": 761,
|
| 6 |
+
"eval_samples_per_second": 29.894,
|
| 7 |
+
"eval_steps_per_second": 3.771,
|
| 8 |
+
"eval_wer": 0.6058069112931956,
|
| 9 |
+
"train_loss": 2.504730513961227,
|
| 10 |
+
"train_runtime": 70530.0839,
|
| 11 |
+
"train_samples": 25915,
|
| 12 |
+
"train_samples_per_second": 18.372,
|
| 13 |
+
"train_steps_per_second": 1.148
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 1.1176735162734985,
|
| 4 |
+
"eval_runtime": 25.4564,
|
| 5 |
+
"eval_samples": 761,
|
| 6 |
+
"eval_samples_per_second": 29.894,
|
| 7 |
+
"eval_steps_per_second": 3.771,
|
| 8 |
+
"eval_wer": 0.6058069112931956
|
| 9 |
+
}
|
runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/events.out.tfevents.1643155382.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4657a8d44f2001a787c1b91e25e9d166759c43e52fba9cd6b4b552c909f3a392
|
| 3 |
+
size 31127
|
runs/Jan26_00-02-24_job-fa775f5b-8438-4c3d-95fa-ed70ddaee577/events.out.tfevents.1643225941.job-fa775f5b-8438-4c3d-95fa-ed70ddaee577.14643.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4441fb64fd51b427eb4dce4a8f47499093fd1ddb004d125cb0998f1fec1172eb
|
| 3 |
+
size 364
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 2.504730513961227,
|
| 4 |
+
"train_runtime": 70530.0839,
|
| 5 |
+
"train_samples": 25915,
|
| 6 |
+
"train_samples_per_second": 18.372,
|
| 7 |
+
"train_steps_per_second": 1.148
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,835 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 81000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.93,
|
| 12 |
+
"learning_rate": 4.983333333333334e-06,
|
| 13 |
+
"loss": 23.3878,
|
| 14 |
+
"step": 1500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.93,
|
| 18 |
+
"eval_loss": 21.917871475219727,
|
| 19 |
+
"eval_runtime": 24.5965,
|
| 20 |
+
"eval_samples_per_second": 30.939,
|
| 21 |
+
"eval_steps_per_second": 3.903,
|
| 22 |
+
"eval_wer": 1.0,
|
| 23 |
+
"step": 1500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.85,
|
| 27 |
+
"learning_rate": 4.905974842767296e-06,
|
| 28 |
+
"loss": 8.8862,
|
| 29 |
+
"step": 3000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.85,
|
| 33 |
+
"eval_loss": 6.059910297393799,
|
| 34 |
+
"eval_runtime": 24.7094,
|
| 35 |
+
"eval_samples_per_second": 30.798,
|
| 36 |
+
"eval_steps_per_second": 3.885,
|
| 37 |
+
"eval_wer": 1.0,
|
| 38 |
+
"step": 3000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.78,
|
| 42 |
+
"learning_rate": 4.811635220125786e-06,
|
| 43 |
+
"loss": 4.3701,
|
| 44 |
+
"step": 4500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.78,
|
| 48 |
+
"eval_loss": 4.383728981018066,
|
| 49 |
+
"eval_runtime": 24.9717,
|
| 50 |
+
"eval_samples_per_second": 30.474,
|
| 51 |
+
"eval_steps_per_second": 3.844,
|
| 52 |
+
"eval_wer": 1.0,
|
| 53 |
+
"step": 4500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.7,
|
| 57 |
+
"learning_rate": 4.717295597484277e-06,
|
| 58 |
+
"loss": 4.113,
|
| 59 |
+
"step": 6000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.7,
|
| 63 |
+
"eval_loss": 4.269829750061035,
|
| 64 |
+
"eval_runtime": 25.0095,
|
| 65 |
+
"eval_samples_per_second": 30.428,
|
| 66 |
+
"eval_steps_per_second": 3.839,
|
| 67 |
+
"eval_wer": 0.9982187388671179,
|
| 68 |
+
"step": 6000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.63,
|
| 72 |
+
"learning_rate": 4.6229559748427675e-06,
|
| 73 |
+
"loss": 3.9666,
|
| 74 |
+
"step": 7500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.63,
|
| 78 |
+
"eval_loss": 3.9726266860961914,
|
| 79 |
+
"eval_runtime": 24.8315,
|
| 80 |
+
"eval_samples_per_second": 30.647,
|
| 81 |
+
"eval_steps_per_second": 3.866,
|
| 82 |
+
"eval_wer": 0.9989312433202707,
|
| 83 |
+
"step": 7500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.56,
|
| 87 |
+
"learning_rate": 4.5286792452830195e-06,
|
| 88 |
+
"loss": 3.5965,
|
| 89 |
+
"step": 9000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.56,
|
| 93 |
+
"eval_loss": 3.712357759475708,
|
| 94 |
+
"eval_runtime": 25.2229,
|
| 95 |
+
"eval_samples_per_second": 30.171,
|
| 96 |
+
"eval_steps_per_second": 3.806,
|
| 97 |
+
"eval_wer": 0.9975062344139651,
|
| 98 |
+
"step": 9000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.48,
|
| 102 |
+
"learning_rate": 4.43433962264151e-06,
|
| 103 |
+
"loss": 3.3944,
|
| 104 |
+
"step": 10500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.48,
|
| 108 |
+
"eval_loss": 3.5005130767822266,
|
| 109 |
+
"eval_runtime": 25.0342,
|
| 110 |
+
"eval_samples_per_second": 30.398,
|
| 111 |
+
"eval_steps_per_second": 3.835,
|
| 112 |
+
"eval_wer": 1.0057000356252226,
|
| 113 |
+
"step": 10500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 7.41,
|
| 117 |
+
"learning_rate": 4.340062893081761e-06,
|
| 118 |
+
"loss": 3.304,
|
| 119 |
+
"step": 12000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 7.41,
|
| 123 |
+
"eval_loss": 3.3709797859191895,
|
| 124 |
+
"eval_runtime": 24.7151,
|
| 125 |
+
"eval_samples_per_second": 30.791,
|
| 126 |
+
"eval_steps_per_second": 3.884,
|
| 127 |
+
"eval_wer": 1.0042750267189169,
|
| 128 |
+
"step": 12000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.33,
|
| 132 |
+
"learning_rate": 4.245723270440252e-06,
|
| 133 |
+
"loss": 3.2482,
|
| 134 |
+
"step": 13500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.33,
|
| 138 |
+
"eval_loss": 3.4201204776763916,
|
| 139 |
+
"eval_runtime": 25.1168,
|
| 140 |
+
"eval_samples_per_second": 30.298,
|
| 141 |
+
"eval_steps_per_second": 3.822,
|
| 142 |
+
"eval_wer": 1.015496971856074,
|
| 143 |
+
"step": 13500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 9.26,
|
| 147 |
+
"learning_rate": 4.151446540880503e-06,
|
| 148 |
+
"loss": 3.212,
|
| 149 |
+
"step": 15000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 9.26,
|
| 153 |
+
"eval_loss": 3.373223304748535,
|
| 154 |
+
"eval_runtime": 24.7052,
|
| 155 |
+
"eval_samples_per_second": 30.803,
|
| 156 |
+
"eval_steps_per_second": 3.886,
|
| 157 |
+
"eval_wer": 1.0151407196294977,
|
| 158 |
+
"step": 15000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.19,
|
| 162 |
+
"learning_rate": 4.057106918238994e-06,
|
| 163 |
+
"loss": 3.1778,
|
| 164 |
+
"step": 16500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.19,
|
| 168 |
+
"eval_loss": 3.2763421535491943,
|
| 169 |
+
"eval_runtime": 25.3297,
|
| 170 |
+
"eval_samples_per_second": 30.044,
|
| 171 |
+
"eval_steps_per_second": 3.79,
|
| 172 |
+
"eval_wer": 1.0008906305664411,
|
| 173 |
+
"step": 16500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 11.11,
|
| 177 |
+
"learning_rate": 3.962767295597484e-06,
|
| 178 |
+
"loss": 3.1027,
|
| 179 |
+
"step": 18000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 11.11,
|
| 183 |
+
"eval_loss": 3.1943371295928955,
|
| 184 |
+
"eval_runtime": 24.6308,
|
| 185 |
+
"eval_samples_per_second": 30.896,
|
| 186 |
+
"eval_steps_per_second": 3.898,
|
| 187 |
+
"eval_wer": 1.0024937655860349,
|
| 188 |
+
"step": 18000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.04,
|
| 192 |
+
"learning_rate": 3.868490566037736e-06,
|
| 193 |
+
"loss": 2.9905,
|
| 194 |
+
"step": 19500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.04,
|
| 198 |
+
"eval_loss": 2.808248281478882,
|
| 199 |
+
"eval_runtime": 24.4561,
|
| 200 |
+
"eval_samples_per_second": 31.117,
|
| 201 |
+
"eval_steps_per_second": 3.925,
|
| 202 |
+
"eval_wer": 0.9702529390808693,
|
| 203 |
+
"step": 19500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 12.96,
|
| 207 |
+
"learning_rate": 3.774213836477988e-06,
|
| 208 |
+
"loss": 2.7095,
|
| 209 |
+
"step": 21000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 12.96,
|
| 213 |
+
"eval_loss": 2.4993014335632324,
|
| 214 |
+
"eval_runtime": 24.4488,
|
| 215 |
+
"eval_samples_per_second": 31.126,
|
| 216 |
+
"eval_steps_per_second": 3.927,
|
| 217 |
+
"eval_wer": 0.9301745635910225,
|
| 218 |
+
"step": 21000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 13.89,
|
| 222 |
+
"learning_rate": 3.6799371069182395e-06,
|
| 223 |
+
"loss": 2.4862,
|
| 224 |
+
"step": 22500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.89,
|
| 228 |
+
"eval_loss": 2.3071722984313965,
|
| 229 |
+
"eval_runtime": 26.0996,
|
| 230 |
+
"eval_samples_per_second": 29.158,
|
| 231 |
+
"eval_steps_per_second": 3.678,
|
| 232 |
+
"eval_wer": 0.9139650872817955,
|
| 233 |
+
"step": 22500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 14.81,
|
| 237 |
+
"learning_rate": 3.58559748427673e-06,
|
| 238 |
+
"loss": 2.3271,
|
| 239 |
+
"step": 24000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 14.81,
|
| 243 |
+
"eval_loss": 2.1398162841796875,
|
| 244 |
+
"eval_runtime": 25.2522,
|
| 245 |
+
"eval_samples_per_second": 30.136,
|
| 246 |
+
"eval_steps_per_second": 3.802,
|
| 247 |
+
"eval_wer": 0.8949055931599572,
|
| 248 |
+
"step": 24000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 15.74,
|
| 252 |
+
"learning_rate": 3.4912578616352204e-06,
|
| 253 |
+
"loss": 2.1968,
|
| 254 |
+
"step": 25500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 15.74,
|
| 258 |
+
"eval_loss": 2.059424877166748,
|
| 259 |
+
"eval_runtime": 24.8853,
|
| 260 |
+
"eval_samples_per_second": 30.58,
|
| 261 |
+
"eval_steps_per_second": 3.858,
|
| 262 |
+
"eval_wer": 0.8817242607766299,
|
| 263 |
+
"step": 25500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 16.67,
|
| 267 |
+
"learning_rate": 3.396981132075472e-06,
|
| 268 |
+
"loss": 2.111,
|
| 269 |
+
"step": 27000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 16.67,
|
| 273 |
+
"eval_loss": 1.9404386281967163,
|
| 274 |
+
"eval_runtime": 24.703,
|
| 275 |
+
"eval_samples_per_second": 30.806,
|
| 276 |
+
"eval_steps_per_second": 3.886,
|
| 277 |
+
"eval_wer": 0.8630210188813681,
|
| 278 |
+
"step": 27000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 17.59,
|
| 282 |
+
"learning_rate": 3.3027044025157235e-06,
|
| 283 |
+
"loss": 2.0387,
|
| 284 |
+
"step": 28500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 17.59,
|
| 288 |
+
"eval_loss": 1.8895297050476074,
|
| 289 |
+
"eval_runtime": 24.8094,
|
| 290 |
+
"eval_samples_per_second": 30.674,
|
| 291 |
+
"eval_steps_per_second": 3.87,
|
| 292 |
+
"eval_wer": 0.8496615603847524,
|
| 293 |
+
"step": 28500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 18.52,
|
| 297 |
+
"learning_rate": 3.208364779874214e-06,
|
| 298 |
+
"loss": 1.9504,
|
| 299 |
+
"step": 30000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 18.52,
|
| 303 |
+
"eval_loss": 1.7960795164108276,
|
| 304 |
+
"eval_runtime": 25.0414,
|
| 305 |
+
"eval_samples_per_second": 30.39,
|
| 306 |
+
"eval_steps_per_second": 3.834,
|
| 307 |
+
"eval_wer": 0.8314926968293552,
|
| 308 |
+
"step": 30000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 19.44,
|
| 312 |
+
"learning_rate": 3.1140880503144657e-06,
|
| 313 |
+
"loss": 1.9039,
|
| 314 |
+
"step": 31500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 19.44,
|
| 318 |
+
"eval_loss": 1.7433359622955322,
|
| 319 |
+
"eval_runtime": 25.2242,
|
| 320 |
+
"eval_samples_per_second": 30.169,
|
| 321 |
+
"eval_steps_per_second": 3.806,
|
| 322 |
+
"eval_wer": 0.8213395083719274,
|
| 323 |
+
"step": 31500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 20.37,
|
| 327 |
+
"learning_rate": 3.0198113207547176e-06,
|
| 328 |
+
"loss": 1.8342,
|
| 329 |
+
"step": 33000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 20.37,
|
| 333 |
+
"eval_loss": 1.679031491279602,
|
| 334 |
+
"eval_runtime": 24.764,
|
| 335 |
+
"eval_samples_per_second": 30.73,
|
| 336 |
+
"eval_steps_per_second": 3.877,
|
| 337 |
+
"eval_wer": 0.7994299964374777,
|
| 338 |
+
"step": 33000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 21.3,
|
| 342 |
+
"learning_rate": 2.9254716981132075e-06,
|
| 343 |
+
"loss": 1.7824,
|
| 344 |
+
"step": 34500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 21.3,
|
| 348 |
+
"eval_loss": 1.6291165351867676,
|
| 349 |
+
"eval_runtime": 25.2561,
|
| 350 |
+
"eval_samples_per_second": 30.131,
|
| 351 |
+
"eval_steps_per_second": 3.801,
|
| 352 |
+
"eval_wer": 0.782508015675098,
|
| 353 |
+
"step": 34500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 22.22,
|
| 357 |
+
"learning_rate": 2.831132075471698e-06,
|
| 358 |
+
"loss": 1.7359,
|
| 359 |
+
"step": 36000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 22.22,
|
| 363 |
+
"eval_loss": 1.578299880027771,
|
| 364 |
+
"eval_runtime": 24.8174,
|
| 365 |
+
"eval_samples_per_second": 30.664,
|
| 366 |
+
"eval_steps_per_second": 3.868,
|
| 367 |
+
"eval_wer": 0.770573566084788,
|
| 368 |
+
"step": 36000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 23.15,
|
| 372 |
+
"learning_rate": 2.73685534591195e-06,
|
| 373 |
+
"loss": 1.7053,
|
| 374 |
+
"step": 37500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 23.15,
|
| 378 |
+
"eval_loss": 1.5247900485992432,
|
| 379 |
+
"eval_runtime": 24.9123,
|
| 380 |
+
"eval_samples_per_second": 30.547,
|
| 381 |
+
"eval_steps_per_second": 3.854,
|
| 382 |
+
"eval_wer": 0.749198432490203,
|
| 383 |
+
"step": 37500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 24.07,
|
| 387 |
+
"learning_rate": 2.6425786163522016e-06,
|
| 388 |
+
"loss": 1.6504,
|
| 389 |
+
"step": 39000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 24.07,
|
| 393 |
+
"eval_loss": 1.4929991960525513,
|
| 394 |
+
"eval_runtime": 26.1656,
|
| 395 |
+
"eval_samples_per_second": 29.084,
|
| 396 |
+
"eval_steps_per_second": 3.669,
|
| 397 |
+
"eval_wer": 0.7406483790523691,
|
| 398 |
+
"step": 39000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 25.0,
|
| 402 |
+
"learning_rate": 2.5482389937106923e-06,
|
| 403 |
+
"loss": 1.6263,
|
| 404 |
+
"step": 40500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 25.0,
|
| 408 |
+
"eval_loss": 1.4572067260742188,
|
| 409 |
+
"eval_runtime": 25.0273,
|
| 410 |
+
"eval_samples_per_second": 30.407,
|
| 411 |
+
"eval_steps_per_second": 3.836,
|
| 412 |
+
"eval_wer": 0.7347702173138582,
|
| 413 |
+
"step": 40500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 25.93,
|
| 417 |
+
"learning_rate": 2.4539622641509434e-06,
|
| 418 |
+
"loss": 1.5893,
|
| 419 |
+
"step": 42000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 25.93,
|
| 423 |
+
"eval_loss": 1.4201958179473877,
|
| 424 |
+
"eval_runtime": 25.1981,
|
| 425 |
+
"eval_samples_per_second": 30.201,
|
| 426 |
+
"eval_steps_per_second": 3.81,
|
| 427 |
+
"eval_wer": 0.7160669754185963,
|
| 428 |
+
"step": 42000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 26.85,
|
| 432 |
+
"learning_rate": 2.359622641509434e-06,
|
| 433 |
+
"loss": 1.5669,
|
| 434 |
+
"step": 43500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 26.85,
|
| 438 |
+
"eval_loss": 1.3987159729003906,
|
| 439 |
+
"eval_runtime": 24.7489,
|
| 440 |
+
"eval_samples_per_second": 30.749,
|
| 441 |
+
"eval_steps_per_second": 3.879,
|
| 442 |
+
"eval_wer": 0.7142857142857143,
|
| 443 |
+
"step": 43500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 27.78,
|
| 447 |
+
"learning_rate": 2.265408805031447e-06,
|
| 448 |
+
"loss": 1.5277,
|
| 449 |
+
"step": 45000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 27.78,
|
| 453 |
+
"eval_loss": 1.3511500358581543,
|
| 454 |
+
"eval_runtime": 25.1221,
|
| 455 |
+
"eval_samples_per_second": 30.292,
|
| 456 |
+
"eval_steps_per_second": 3.821,
|
| 457 |
+
"eval_wer": 0.6991449946562166,
|
| 458 |
+
"step": 45000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 28.7,
|
| 462 |
+
"learning_rate": 2.1710691823899376e-06,
|
| 463 |
+
"loss": 1.501,
|
| 464 |
+
"step": 46500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 28.7,
|
| 468 |
+
"eval_loss": 1.331958532333374,
|
| 469 |
+
"eval_runtime": 24.626,
|
| 470 |
+
"eval_samples_per_second": 30.902,
|
| 471 |
+
"eval_steps_per_second": 3.898,
|
| 472 |
+
"eval_wer": 0.6879230495190595,
|
| 473 |
+
"step": 46500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 29.63,
|
| 477 |
+
"learning_rate": 2.076729559748428e-06,
|
| 478 |
+
"loss": 1.4781,
|
| 479 |
+
"step": 48000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 29.63,
|
| 483 |
+
"eval_loss": 1.3111568689346313,
|
| 484 |
+
"eval_runtime": 24.7067,
|
| 485 |
+
"eval_samples_per_second": 30.801,
|
| 486 |
+
"eval_steps_per_second": 3.886,
|
| 487 |
+
"eval_wer": 0.6788386177413609,
|
| 488 |
+
"step": 48000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 30.56,
|
| 492 |
+
"learning_rate": 1.9824528301886794e-06,
|
| 493 |
+
"loss": 1.4477,
|
| 494 |
+
"step": 49500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 30.56,
|
| 498 |
+
"eval_loss": 1.2850154638290405,
|
| 499 |
+
"eval_runtime": 24.9276,
|
| 500 |
+
"eval_samples_per_second": 30.528,
|
| 501 |
+
"eval_steps_per_second": 3.851,
|
| 502 |
+
"eval_wer": 0.6656572853580335,
|
| 503 |
+
"step": 49500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 31.48,
|
| 507 |
+
"learning_rate": 1.888176100628931e-06,
|
| 508 |
+
"loss": 1.4483,
|
| 509 |
+
"step": 51000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 31.48,
|
| 513 |
+
"eval_loss": 1.2812527418136597,
|
| 514 |
+
"eval_runtime": 25.2119,
|
| 515 |
+
"eval_samples_per_second": 30.184,
|
| 516 |
+
"eval_steps_per_second": 3.808,
|
| 517 |
+
"eval_wer": 0.6633416458852868,
|
| 518 |
+
"step": 51000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 32.41,
|
| 522 |
+
"learning_rate": 1.7938364779874214e-06,
|
| 523 |
+
"loss": 1.4065,
|
| 524 |
+
"step": 52500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 32.41,
|
| 528 |
+
"eval_loss": 1.2474950551986694,
|
| 529 |
+
"eval_runtime": 25.9366,
|
| 530 |
+
"eval_samples_per_second": 29.341,
|
| 531 |
+
"eval_steps_per_second": 3.701,
|
| 532 |
+
"eval_wer": 0.6540790879942999,
|
| 533 |
+
"step": 52500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 33.33,
|
| 537 |
+
"learning_rate": 1.699496855345912e-06,
|
| 538 |
+
"loss": 1.3779,
|
| 539 |
+
"step": 54000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 33.33,
|
| 543 |
+
"eval_loss": 1.224350929260254,
|
| 544 |
+
"eval_runtime": 25.3174,
|
| 545 |
+
"eval_samples_per_second": 30.058,
|
| 546 |
+
"eval_steps_per_second": 3.792,
|
| 547 |
+
"eval_wer": 0.6503384396152476,
|
| 548 |
+
"step": 54000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 34.26,
|
| 552 |
+
"learning_rate": 1.6052830188679247e-06,
|
| 553 |
+
"loss": 1.3788,
|
| 554 |
+
"step": 55500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 34.26,
|
| 558 |
+
"eval_loss": 1.2116361856460571,
|
| 559 |
+
"eval_runtime": 24.9096,
|
| 560 |
+
"eval_samples_per_second": 30.551,
|
| 561 |
+
"eval_steps_per_second": 3.854,
|
| 562 |
+
"eval_wer": 0.6407196294976844,
|
| 563 |
+
"step": 55500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 35.19,
|
| 567 |
+
"learning_rate": 1.5109433962264154e-06,
|
| 568 |
+
"loss": 1.3428,
|
| 569 |
+
"step": 57000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 35.19,
|
| 573 |
+
"eval_loss": 1.1938250064849854,
|
| 574 |
+
"eval_runtime": 24.9601,
|
| 575 |
+
"eval_samples_per_second": 30.489,
|
| 576 |
+
"eval_steps_per_second": 3.846,
|
| 577 |
+
"eval_wer": 0.6351977199857499,
|
| 578 |
+
"step": 57000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 36.11,
|
| 582 |
+
"learning_rate": 1.4166666666666667e-06,
|
| 583 |
+
"loss": 1.3453,
|
| 584 |
+
"step": 58500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 36.11,
|
| 588 |
+
"eval_loss": 1.192725419998169,
|
| 589 |
+
"eval_runtime": 25.8368,
|
| 590 |
+
"eval_samples_per_second": 29.454,
|
| 591 |
+
"eval_steps_per_second": 3.716,
|
| 592 |
+
"eval_wer": 0.6339508371927325,
|
| 593 |
+
"step": 58500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 37.04,
|
| 597 |
+
"learning_rate": 1.3223270440251574e-06,
|
| 598 |
+
"loss": 1.3137,
|
| 599 |
+
"step": 60000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 37.04,
|
| 603 |
+
"eval_loss": 1.16991126537323,
|
| 604 |
+
"eval_runtime": 24.7736,
|
| 605 |
+
"eval_samples_per_second": 30.718,
|
| 606 |
+
"eval_steps_per_second": 3.875,
|
| 607 |
+
"eval_wer": 0.6252226576416102,
|
| 608 |
+
"step": 60000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 37.96,
|
| 612 |
+
"learning_rate": 1.2279874213836478e-06,
|
| 613 |
+
"loss": 1.2984,
|
| 614 |
+
"step": 61500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 37.96,
|
| 618 |
+
"eval_loss": 1.1666393280029297,
|
| 619 |
+
"eval_runtime": 24.7631,
|
| 620 |
+
"eval_samples_per_second": 30.731,
|
| 621 |
+
"eval_steps_per_second": 3.877,
|
| 622 |
+
"eval_wer": 0.6229070181688635,
|
| 623 |
+
"step": 61500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 38.89,
|
| 627 |
+
"learning_rate": 1.1337106918238996e-06,
|
| 628 |
+
"loss": 1.2927,
|
| 629 |
+
"step": 63000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 38.89,
|
| 633 |
+
"eval_loss": 1.1585460901260376,
|
| 634 |
+
"eval_runtime": 24.9605,
|
| 635 |
+
"eval_samples_per_second": 30.488,
|
| 636 |
+
"eval_steps_per_second": 3.846,
|
| 637 |
+
"eval_wer": 0.6188101175632348,
|
| 638 |
+
"step": 63000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 39.81,
|
| 642 |
+
"learning_rate": 1.039433962264151e-06,
|
| 643 |
+
"loss": 1.2919,
|
| 644 |
+
"step": 64500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 39.81,
|
| 648 |
+
"eval_loss": 1.1618481874465942,
|
| 649 |
+
"eval_runtime": 24.6184,
|
| 650 |
+
"eval_samples_per_second": 30.912,
|
| 651 |
+
"eval_steps_per_second": 3.9,
|
| 652 |
+
"eval_wer": 0.6189882436765229,
|
| 653 |
+
"step": 64500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 40.74,
|
| 657 |
+
"learning_rate": 9.450943396226415e-07,
|
| 658 |
+
"loss": 1.293,
|
| 659 |
+
"step": 66000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 40.74,
|
| 663 |
+
"eval_loss": 1.147918462753296,
|
| 664 |
+
"eval_runtime": 24.8441,
|
| 665 |
+
"eval_samples_per_second": 30.631,
|
| 666 |
+
"eval_steps_per_second": 3.864,
|
| 667 |
+
"eval_wer": 0.6180976131100819,
|
| 668 |
+
"step": 66000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 41.67,
|
| 672 |
+
"learning_rate": 8.507547169811322e-07,
|
| 673 |
+
"loss": 1.2853,
|
| 674 |
+
"step": 67500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 41.67,
|
| 678 |
+
"eval_loss": 1.1422728300094604,
|
| 679 |
+
"eval_runtime": 24.5674,
|
| 680 |
+
"eval_samples_per_second": 30.976,
|
| 681 |
+
"eval_steps_per_second": 3.908,
|
| 682 |
+
"eval_wer": 0.6202351264695405,
|
| 683 |
+
"step": 67500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 42.59,
|
| 687 |
+
"learning_rate": 7.565408805031447e-07,
|
| 688 |
+
"loss": 1.2687,
|
| 689 |
+
"step": 69000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 42.59,
|
| 693 |
+
"eval_loss": 1.131521224975586,
|
| 694 |
+
"eval_runtime": 24.9081,
|
| 695 |
+
"eval_samples_per_second": 30.552,
|
| 696 |
+
"eval_steps_per_second": 3.854,
|
| 697 |
+
"eval_wer": 0.6131100819380121,
|
| 698 |
+
"step": 69000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 43.52,
|
| 702 |
+
"learning_rate": 6.622012578616354e-07,
|
| 703 |
+
"loss": 1.2603,
|
| 704 |
+
"step": 70500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 43.52,
|
| 708 |
+
"eval_loss": 1.133251428604126,
|
| 709 |
+
"eval_runtime": 25.026,
|
| 710 |
+
"eval_samples_per_second": 30.408,
|
| 711 |
+
"eval_steps_per_second": 3.836,
|
| 712 |
+
"eval_wer": 0.6127538297114357,
|
| 713 |
+
"step": 70500
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 44.44,
|
| 717 |
+
"learning_rate": 5.678616352201258e-07,
|
| 718 |
+
"loss": 1.2577,
|
| 719 |
+
"step": 72000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 44.44,
|
| 723 |
+
"eval_loss": 1.1190848350524902,
|
| 724 |
+
"eval_runtime": 24.839,
|
| 725 |
+
"eval_samples_per_second": 30.637,
|
| 726 |
+
"eval_steps_per_second": 3.865,
|
| 727 |
+
"eval_wer": 0.6079444246526541,
|
| 728 |
+
"step": 72000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 45.37,
|
| 732 |
+
"learning_rate": 4.7358490566037737e-07,
|
| 733 |
+
"loss": 1.2435,
|
| 734 |
+
"step": 73500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 45.37,
|
| 738 |
+
"eval_loss": 1.1177417039871216,
|
| 739 |
+
"eval_runtime": 24.5078,
|
| 740 |
+
"eval_samples_per_second": 31.051,
|
| 741 |
+
"eval_steps_per_second": 3.917,
|
| 742 |
+
"eval_wer": 0.6079444246526541,
|
| 743 |
+
"step": 73500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 46.3,
|
| 747 |
+
"learning_rate": 3.79245283018868e-07,
|
| 748 |
+
"loss": 1.251,
|
| 749 |
+
"step": 75000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 46.3,
|
| 753 |
+
"eval_loss": 1.1210719347000122,
|
| 754 |
+
"eval_runtime": 24.6592,
|
| 755 |
+
"eval_samples_per_second": 30.861,
|
| 756 |
+
"eval_steps_per_second": 3.893,
|
| 757 |
+
"eval_wer": 0.6091913074456715,
|
| 758 |
+
"step": 75000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 47.22,
|
| 762 |
+
"learning_rate": 2.8496855345911953e-07,
|
| 763 |
+
"loss": 1.2482,
|
| 764 |
+
"step": 76500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 47.22,
|
| 768 |
+
"eval_loss": 1.1177067756652832,
|
| 769 |
+
"eval_runtime": 25.1033,
|
| 770 |
+
"eval_samples_per_second": 30.315,
|
| 771 |
+
"eval_steps_per_second": 3.824,
|
| 772 |
+
"eval_wer": 0.6059850374064838,
|
| 773 |
+
"step": 76500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 48.15,
|
| 777 |
+
"learning_rate": 1.9062893081761006e-07,
|
| 778 |
+
"loss": 1.2422,
|
| 779 |
+
"step": 78000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 48.15,
|
| 783 |
+
"eval_loss": 1.1227455139160156,
|
| 784 |
+
"eval_runtime": 25.3506,
|
| 785 |
+
"eval_samples_per_second": 30.019,
|
| 786 |
+
"eval_steps_per_second": 3.787,
|
| 787 |
+
"eval_wer": 0.6097256857855362,
|
| 788 |
+
"step": 78000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 49.07,
|
| 792 |
+
"learning_rate": 9.641509433962265e-08,
|
| 793 |
+
"loss": 1.2485,
|
| 794 |
+
"step": 79500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 49.07,
|
| 798 |
+
"eval_loss": 1.1186823844909668,
|
| 799 |
+
"eval_runtime": 24.6079,
|
| 800 |
+
"eval_samples_per_second": 30.925,
|
| 801 |
+
"eval_steps_per_second": 3.901,
|
| 802 |
+
"eval_wer": 0.6070537940862131,
|
| 803 |
+
"step": 79500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 50.0,
|
| 807 |
+
"learning_rate": 2.138364779874214e-09,
|
| 808 |
+
"loss": 1.2425,
|
| 809 |
+
"step": 81000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 50.0,
|
| 813 |
+
"eval_loss": 1.1176735162734985,
|
| 814 |
+
"eval_runtime": 24.8722,
|
| 815 |
+
"eval_samples_per_second": 30.596,
|
| 816 |
+
"eval_steps_per_second": 3.86,
|
| 817 |
+
"eval_wer": 0.6058069112931956,
|
| 818 |
+
"step": 81000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 50.0,
|
| 822 |
+
"step": 81000,
|
| 823 |
+
"total_flos": 1.7056142305765743e+20,
|
| 824 |
+
"train_loss": 2.504730513961227,
|
| 825 |
+
"train_runtime": 70530.0839,
|
| 826 |
+
"train_samples_per_second": 18.372,
|
| 827 |
+
"train_steps_per_second": 1.148
|
| 828 |
+
}
|
| 829 |
+
],
|
| 830 |
+
"max_steps": 81000,
|
| 831 |
+
"num_train_epochs": 50,
|
| 832 |
+
"total_flos": 1.7056142305765743e+20,
|
| 833 |
+
"trial_name": null,
|
| 834 |
+
"trial_params": null
|
| 835 |
+
}
|