Commit
•
39801da
1
Parent(s):
badf00b
Upload trainer_state.json
Browse files- trainer_state.json +1186 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,1186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.657169990503323,
|
| 5 |
+
"global_step": 15600,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.51,
|
| 12 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 13 |
+
"loss": 14.0657,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.51,
|
| 18 |
+
"eval_loss": 6.884028911590576,
|
| 19 |
+
"eval_runtime": 316.7633,
|
| 20 |
+
"eval_samples_per_second": 7.217,
|
| 21 |
+
"eval_steps_per_second": 0.903,
|
| 22 |
+
"eval_wer": 1.3018771418341772,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.02,
|
| 27 |
+
"learning_rate": 3.960000000000001e-05,
|
| 28 |
+
"loss": 6.1255,
|
| 29 |
+
"step": 400
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.02,
|
| 33 |
+
"eval_loss": 3.8771634101867676,
|
| 34 |
+
"eval_runtime": 322.5603,
|
| 35 |
+
"eval_samples_per_second": 7.087,
|
| 36 |
+
"eval_steps_per_second": 0.887,
|
| 37 |
+
"eval_wer": 1.0,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.52,
|
| 42 |
+
"learning_rate": 5.96e-05,
|
| 43 |
+
"loss": 3.2311,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.52,
|
| 48 |
+
"eval_loss": 3.20473313331604,
|
| 49 |
+
"eval_runtime": 316.4632,
|
| 50 |
+
"eval_samples_per_second": 7.224,
|
| 51 |
+
"eval_steps_per_second": 0.904,
|
| 52 |
+
"eval_wer": 0.999386220653675,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.03,
|
| 57 |
+
"learning_rate": 7.960000000000001e-05,
|
| 58 |
+
"loss": 3.1379,
|
| 59 |
+
"step": 800
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.03,
|
| 63 |
+
"eval_loss": 3.1962826251983643,
|
| 64 |
+
"eval_runtime": 316.7959,
|
| 65 |
+
"eval_samples_per_second": 7.216,
|
| 66 |
+
"eval_steps_per_second": 0.903,
|
| 67 |
+
"eval_wer": 0.999386220653675,
|
| 68 |
+
"step": 800
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.54,
|
| 72 |
+
"learning_rate": 9.960000000000001e-05,
|
| 73 |
+
"loss": 2.7389,
|
| 74 |
+
"step": 1000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.54,
|
| 78 |
+
"eval_loss": 1.8025017976760864,
|
| 79 |
+
"eval_runtime": 318.5421,
|
| 80 |
+
"eval_samples_per_second": 7.176,
|
| 81 |
+
"eval_steps_per_second": 0.898,
|
| 82 |
+
"eval_wer": 0.7388880364175745,
|
| 83 |
+
"step": 1000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.05,
|
| 87 |
+
"learning_rate": 9.913427561837456e-05,
|
| 88 |
+
"loss": 1.1799,
|
| 89 |
+
"step": 1200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 3.05,
|
| 93 |
+
"eval_loss": 0.5602023601531982,
|
| 94 |
+
"eval_runtime": 320.0374,
|
| 95 |
+
"eval_samples_per_second": 7.143,
|
| 96 |
+
"eval_steps_per_second": 0.894,
|
| 97 |
+
"eval_wer": 0.3688302388624623,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.55,
|
| 102 |
+
"learning_rate": 9.825088339222615e-05,
|
| 103 |
+
"loss": 0.5985,
|
| 104 |
+
"step": 1400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.55,
|
| 108 |
+
"eval_loss": 0.46469706296920776,
|
| 109 |
+
"eval_runtime": 317.0532,
|
| 110 |
+
"eval_samples_per_second": 7.21,
|
| 111 |
+
"eval_steps_per_second": 0.902,
|
| 112 |
+
"eval_wer": 0.3150222495013043,
|
| 113 |
+
"step": 1400
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.06,
|
| 117 |
+
"learning_rate": 9.736749116607774e-05,
|
| 118 |
+
"loss": 0.4944,
|
| 119 |
+
"step": 1600
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.06,
|
| 123 |
+
"eval_loss": 0.38040226697921753,
|
| 124 |
+
"eval_runtime": 319.5077,
|
| 125 |
+
"eval_samples_per_second": 7.155,
|
| 126 |
+
"eval_steps_per_second": 0.895,
|
| 127 |
+
"eval_wer": 0.28331031660784617,
|
| 128 |
+
"step": 1600
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.57,
|
| 132 |
+
"learning_rate": 9.648409893992934e-05,
|
| 133 |
+
"loss": 0.4011,
|
| 134 |
+
"step": 1800
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.57,
|
| 138 |
+
"eval_loss": 0.3565872609615326,
|
| 139 |
+
"eval_runtime": 326.4601,
|
| 140 |
+
"eval_samples_per_second": 7.002,
|
| 141 |
+
"eval_steps_per_second": 0.876,
|
| 142 |
+
"eval_wer": 0.2767121886348524,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 5.08,
|
| 147 |
+
"learning_rate": 9.560070671378091e-05,
|
| 148 |
+
"loss": 0.355,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.08,
|
| 153 |
+
"eval_loss": 0.33882376551628113,
|
| 154 |
+
"eval_runtime": 327.1229,
|
| 155 |
+
"eval_samples_per_second": 6.988,
|
| 156 |
+
"eval_steps_per_second": 0.874,
|
| 157 |
+
"eval_wer": 0.26934683647895247,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 5.58,
|
| 162 |
+
"learning_rate": 9.471731448763252e-05,
|
| 163 |
+
"loss": 0.3319,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.58,
|
| 168 |
+
"eval_loss": 0.3453792929649353,
|
| 169 |
+
"eval_runtime": 327.4176,
|
| 170 |
+
"eval_samples_per_second": 6.982,
|
| 171 |
+
"eval_steps_per_second": 0.874,
|
| 172 |
+
"eval_wer": 0.2657153086798629,
|
| 173 |
+
"step": 2200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 6.09,
|
| 177 |
+
"learning_rate": 9.383392226148411e-05,
|
| 178 |
+
"loss": 0.3052,
|
| 179 |
+
"step": 2400
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 6.09,
|
| 183 |
+
"eval_loss": 0.3088168799877167,
|
| 184 |
+
"eval_runtime": 328.7404,
|
| 185 |
+
"eval_samples_per_second": 6.954,
|
| 186 |
+
"eval_steps_per_second": 0.87,
|
| 187 |
+
"eval_wer": 0.2609073704669838,
|
| 188 |
+
"step": 2400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.6,
|
| 192 |
+
"learning_rate": 9.295053003533569e-05,
|
| 193 |
+
"loss": 0.2707,
|
| 194 |
+
"step": 2600
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.6,
|
| 198 |
+
"eval_loss": 0.3140409290790558,
|
| 199 |
+
"eval_runtime": 329.2489,
|
| 200 |
+
"eval_samples_per_second": 6.943,
|
| 201 |
+
"eval_steps_per_second": 0.869,
|
| 202 |
+
"eval_wer": 0.25297938724361924,
|
| 203 |
+
"step": 2600
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 7.11,
|
| 207 |
+
"learning_rate": 9.206713780918729e-05,
|
| 208 |
+
"loss": 0.2603,
|
| 209 |
+
"step": 2800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 7.11,
|
| 213 |
+
"eval_loss": 0.43849411606788635,
|
| 214 |
+
"eval_runtime": 330.8014,
|
| 215 |
+
"eval_samples_per_second": 6.91,
|
| 216 |
+
"eval_steps_per_second": 0.865,
|
| 217 |
+
"eval_wer": 0.2776328576543399,
|
| 218 |
+
"step": 2800
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.61,
|
| 222 |
+
"learning_rate": 9.118374558303887e-05,
|
| 223 |
+
"loss": 0.2559,
|
| 224 |
+
"step": 3000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.61,
|
| 228 |
+
"eval_loss": 0.28870412707328796,
|
| 229 |
+
"eval_runtime": 328.263,
|
| 230 |
+
"eval_samples_per_second": 6.964,
|
| 231 |
+
"eval_steps_per_second": 0.871,
|
| 232 |
+
"eval_wer": 0.24919441460794844,
|
| 233 |
+
"step": 3000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.12,
|
| 237 |
+
"learning_rate": 9.030035335689046e-05,
|
| 238 |
+
"loss": 0.231,
|
| 239 |
+
"step": 3200
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 8.12,
|
| 243 |
+
"eval_loss": 0.2984590232372284,
|
| 244 |
+
"eval_runtime": 329.584,
|
| 245 |
+
"eval_samples_per_second": 6.936,
|
| 246 |
+
"eval_steps_per_second": 0.868,
|
| 247 |
+
"eval_wer": 0.24812030075187969,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.63,
|
| 252 |
+
"learning_rate": 8.941696113074205e-05,
|
| 253 |
+
"loss": 0.2194,
|
| 254 |
+
"step": 3400
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.63,
|
| 258 |
+
"eval_loss": 0.33247044682502747,
|
| 259 |
+
"eval_runtime": 325.7403,
|
| 260 |
+
"eval_samples_per_second": 7.018,
|
| 261 |
+
"eval_steps_per_second": 0.878,
|
| 262 |
+
"eval_wer": 0.2547184287248734,
|
| 263 |
+
"step": 3400
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.14,
|
| 267 |
+
"learning_rate": 8.853356890459364e-05,
|
| 268 |
+
"loss": 0.2205,
|
| 269 |
+
"step": 3600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.14,
|
| 273 |
+
"eval_loss": 0.2854120135307312,
|
| 274 |
+
"eval_runtime": 323.7366,
|
| 275 |
+
"eval_samples_per_second": 7.061,
|
| 276 |
+
"eval_steps_per_second": 0.883,
|
| 277 |
+
"eval_wer": 0.2446933660682318,
|
| 278 |
+
"step": 3600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.64,
|
| 282 |
+
"learning_rate": 8.765017667844523e-05,
|
| 283 |
+
"loss": 0.1904,
|
| 284 |
+
"step": 3800
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.64,
|
| 288 |
+
"eval_loss": 0.26710790395736694,
|
| 289 |
+
"eval_runtime": 322.8659,
|
| 290 |
+
"eval_samples_per_second": 7.08,
|
| 291 |
+
"eval_steps_per_second": 0.886,
|
| 292 |
+
"eval_wer": 0.24346580737558182,
|
| 293 |
+
"step": 3800
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 10.15,
|
| 297 |
+
"learning_rate": 8.676678445229682e-05,
|
| 298 |
+
"loss": 0.187,
|
| 299 |
+
"step": 4000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.15,
|
| 303 |
+
"eval_loss": 0.2750653624534607,
|
| 304 |
+
"eval_runtime": 323.9203,
|
| 305 |
+
"eval_samples_per_second": 7.057,
|
| 306 |
+
"eval_steps_per_second": 0.883,
|
| 307 |
+
"eval_wer": 0.2428008797503964,
|
| 308 |
+
"step": 4000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 10.66,
|
| 312 |
+
"learning_rate": 8.588339222614842e-05,
|
| 313 |
+
"loss": 0.1724,
|
| 314 |
+
"step": 4200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 10.66,
|
| 318 |
+
"eval_loss": 0.2918902337551117,
|
| 319 |
+
"eval_runtime": 340.4683,
|
| 320 |
+
"eval_samples_per_second": 6.714,
|
| 321 |
+
"eval_steps_per_second": 0.84,
|
| 322 |
+
"eval_wer": 0.24049920720167767,
|
| 323 |
+
"step": 4200
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 11.17,
|
| 327 |
+
"learning_rate": 8.5e-05,
|
| 328 |
+
"loss": 0.1666,
|
| 329 |
+
"step": 4400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 11.17,
|
| 333 |
+
"eval_loss": 0.28774362802505493,
|
| 334 |
+
"eval_runtime": 342.0819,
|
| 335 |
+
"eval_samples_per_second": 6.683,
|
| 336 |
+
"eval_steps_per_second": 0.836,
|
| 337 |
+
"eval_wer": 0.23799294153751727,
|
| 338 |
+
"step": 4400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 11.67,
|
| 342 |
+
"learning_rate": 8.412102473498234e-05,
|
| 343 |
+
"loss": 0.1562,
|
| 344 |
+
"step": 4600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 11.67,
|
| 348 |
+
"eval_loss": 0.2777426540851593,
|
| 349 |
+
"eval_runtime": 341.5835,
|
| 350 |
+
"eval_samples_per_second": 6.692,
|
| 351 |
+
"eval_steps_per_second": 0.837,
|
| 352 |
+
"eval_wer": 0.2387090174415631,
|
| 353 |
+
"step": 4600
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 12.18,
|
| 357 |
+
"learning_rate": 8.323763250883393e-05,
|
| 358 |
+
"loss": 0.1489,
|
| 359 |
+
"step": 4800
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 12.18,
|
| 363 |
+
"eval_loss": 0.27934086322784424,
|
| 364 |
+
"eval_runtime": 342.4524,
|
| 365 |
+
"eval_samples_per_second": 6.675,
|
| 366 |
+
"eval_steps_per_second": 0.835,
|
| 367 |
+
"eval_wer": 0.24014116924965476,
|
| 368 |
+
"step": 4800
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 12.69,
|
| 372 |
+
"learning_rate": 8.235424028268552e-05,
|
| 373 |
+
"loss": 0.1567,
|
| 374 |
+
"step": 5000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 12.69,
|
| 378 |
+
"eval_loss": 0.29788124561309814,
|
| 379 |
+
"eval_runtime": 339.8038,
|
| 380 |
+
"eval_samples_per_second": 6.727,
|
| 381 |
+
"eval_steps_per_second": 0.842,
|
| 382 |
+
"eval_wer": 0.2369188276814485,
|
| 383 |
+
"step": 5000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 13.2,
|
| 387 |
+
"learning_rate": 8.147084805653711e-05,
|
| 388 |
+
"loss": 0.1501,
|
| 389 |
+
"step": 5200
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 13.2,
|
| 393 |
+
"eval_loss": 0.3033454418182373,
|
| 394 |
+
"eval_runtime": 338.8207,
|
| 395 |
+
"eval_samples_per_second": 6.747,
|
| 396 |
+
"eval_steps_per_second": 0.844,
|
| 397 |
+
"eval_wer": 0.23543552759449646,
|
| 398 |
+
"step": 5200
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 13.7,
|
| 402 |
+
"learning_rate": 8.058745583038869e-05,
|
| 403 |
+
"loss": 0.1362,
|
| 404 |
+
"step": 5400
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 13.7,
|
| 408 |
+
"eval_loss": 0.282699853181839,
|
| 409 |
+
"eval_runtime": 343.5056,
|
| 410 |
+
"eval_samples_per_second": 6.655,
|
| 411 |
+
"eval_steps_per_second": 0.833,
|
| 412 |
+
"eval_wer": 0.23144596184338398,
|
| 413 |
+
"step": 5400
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 14.21,
|
| 417 |
+
"learning_rate": 7.970406360424029e-05,
|
| 418 |
+
"loss": 0.1391,
|
| 419 |
+
"step": 5600
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 14.21,
|
| 423 |
+
"eval_loss": 0.30705466866493225,
|
| 424 |
+
"eval_runtime": 342.7503,
|
| 425 |
+
"eval_samples_per_second": 6.67,
|
| 426 |
+
"eval_steps_per_second": 0.834,
|
| 427 |
+
"eval_wer": 0.2315482584011048,
|
| 428 |
+
"step": 5600
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 14.72,
|
| 432 |
+
"learning_rate": 7.882067137809188e-05,
|
| 433 |
+
"loss": 0.1299,
|
| 434 |
+
"step": 5800
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 14.72,
|
| 438 |
+
"eval_loss": 0.2924181818962097,
|
| 439 |
+
"eval_runtime": 343.6951,
|
| 440 |
+
"eval_samples_per_second": 6.651,
|
| 441 |
+
"eval_steps_per_second": 0.832,
|
| 442 |
+
"eval_wer": 0.23093447905477982,
|
| 443 |
+
"step": 5800
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 15.23,
|
| 447 |
+
"learning_rate": 7.793727915194346e-05,
|
| 448 |
+
"loss": 0.1187,
|
| 449 |
+
"step": 6000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 15.23,
|
| 453 |
+
"eval_loss": 0.31287097930908203,
|
| 454 |
+
"eval_runtime": 343.6023,
|
| 455 |
+
"eval_samples_per_second": 6.653,
|
| 456 |
+
"eval_steps_per_second": 0.832,
|
| 457 |
+
"eval_wer": 0.2343102654595673,
|
| 458 |
+
"step": 6000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 15.74,
|
| 462 |
+
"learning_rate": 7.705388692579506e-05,
|
| 463 |
+
"loss": 0.121,
|
| 464 |
+
"step": 6200
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 15.74,
|
| 468 |
+
"eval_loss": 0.3056861162185669,
|
| 469 |
+
"eval_runtime": 343.3615,
|
| 470 |
+
"eval_samples_per_second": 6.658,
|
| 471 |
+
"eval_steps_per_second": 0.833,
|
| 472 |
+
"eval_wer": 0.23139481356452354,
|
| 473 |
+
"step": 6200
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 16.24,
|
| 477 |
+
"learning_rate": 7.617049469964664e-05,
|
| 478 |
+
"loss": 0.1237,
|
| 479 |
+
"step": 6400
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 16.24,
|
| 483 |
+
"eval_loss": 0.33616331219673157,
|
| 484 |
+
"eval_runtime": 348.2247,
|
| 485 |
+
"eval_samples_per_second": 6.565,
|
| 486 |
+
"eval_steps_per_second": 0.821,
|
| 487 |
+
"eval_wer": 0.2368676794025881,
|
| 488 |
+
"step": 6400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 16.75,
|
| 492 |
+
"learning_rate": 7.528710247349823e-05,
|
| 493 |
+
"loss": 0.1257,
|
| 494 |
+
"step": 6600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 16.75,
|
| 498 |
+
"eval_loss": 0.30364322662353516,
|
| 499 |
+
"eval_runtime": 354.4023,
|
| 500 |
+
"eval_samples_per_second": 6.45,
|
| 501 |
+
"eval_steps_per_second": 0.807,
|
| 502 |
+
"eval_wer": 0.23067873766047772,
|
| 503 |
+
"step": 6600
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 17.26,
|
| 507 |
+
"learning_rate": 7.440371024734982e-05,
|
| 508 |
+
"loss": 0.1151,
|
| 509 |
+
"step": 6800
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 17.26,
|
| 513 |
+
"eval_loss": 0.3333089351654053,
|
| 514 |
+
"eval_runtime": 353.6951,
|
| 515 |
+
"eval_samples_per_second": 6.463,
|
| 516 |
+
"eval_steps_per_second": 0.809,
|
| 517 |
+
"eval_wer": 0.23103677561250063,
|
| 518 |
+
"step": 6800
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 17.77,
|
| 522 |
+
"learning_rate": 7.352031802120141e-05,
|
| 523 |
+
"loss": 0.1045,
|
| 524 |
+
"step": 7000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 17.77,
|
| 528 |
+
"eval_loss": 0.31175628304481506,
|
| 529 |
+
"eval_runtime": 340.1327,
|
| 530 |
+
"eval_samples_per_second": 6.721,
|
| 531 |
+
"eval_steps_per_second": 0.841,
|
| 532 |
+
"eval_wer": 0.23415682062298604,
|
| 533 |
+
"step": 7000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 18.27,
|
| 537 |
+
"learning_rate": 7.2636925795053e-05,
|
| 538 |
+
"loss": 0.114,
|
| 539 |
+
"step": 7200
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 18.27,
|
| 543 |
+
"eval_loss": 0.2973700165748596,
|
| 544 |
+
"eval_runtime": 331.883,
|
| 545 |
+
"eval_samples_per_second": 6.888,
|
| 546 |
+
"eval_steps_per_second": 0.862,
|
| 547 |
+
"eval_wer": 0.2294000306889673,
|
| 548 |
+
"step": 7200
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 18.78,
|
| 552 |
+
"learning_rate": 7.17535335689046e-05,
|
| 553 |
+
"loss": 0.1064,
|
| 554 |
+
"step": 7400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 18.78,
|
| 558 |
+
"eval_loss": 0.3128357529640198,
|
| 559 |
+
"eval_runtime": 340.1178,
|
| 560 |
+
"eval_samples_per_second": 6.721,
|
| 561 |
+
"eval_steps_per_second": 0.841,
|
| 562 |
+
"eval_wer": 0.22837706511175898,
|
| 563 |
+
"step": 7400
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 19.29,
|
| 567 |
+
"learning_rate": 7.087014134275619e-05,
|
| 568 |
+
"loss": 0.1009,
|
| 569 |
+
"step": 7600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 19.29,
|
| 573 |
+
"eval_loss": 0.31967654824256897,
|
| 574 |
+
"eval_runtime": 336.3559,
|
| 575 |
+
"eval_samples_per_second": 6.796,
|
| 576 |
+
"eval_steps_per_second": 0.85,
|
| 577 |
+
"eval_wer": 0.2297069203621298,
|
| 578 |
+
"step": 7600
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 19.8,
|
| 582 |
+
"learning_rate": 6.998674911660778e-05,
|
| 583 |
+
"loss": 0.1047,
|
| 584 |
+
"step": 7800
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 19.8,
|
| 588 |
+
"eval_loss": 0.2982560694217682,
|
| 589 |
+
"eval_runtime": 324.6466,
|
| 590 |
+
"eval_samples_per_second": 7.042,
|
| 591 |
+
"eval_steps_per_second": 0.881,
|
| 592 |
+
"eval_wer": 0.2346171551327298,
|
| 593 |
+
"step": 7800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 20.3,
|
| 597 |
+
"learning_rate": 6.910335689045937e-05,
|
| 598 |
+
"loss": 0.0989,
|
| 599 |
+
"step": 8000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 20.3,
|
| 603 |
+
"eval_loss": 0.3321704864501953,
|
| 604 |
+
"eval_runtime": 325.4996,
|
| 605 |
+
"eval_samples_per_second": 7.023,
|
| 606 |
+
"eval_steps_per_second": 0.879,
|
| 607 |
+
"eval_wer": 0.23170170323768605,
|
| 608 |
+
"step": 8000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 20.81,
|
| 612 |
+
"learning_rate": 6.821996466431095e-05,
|
| 613 |
+
"loss": 0.0976,
|
| 614 |
+
"step": 8200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 20.81,
|
| 618 |
+
"eval_loss": 0.3263297379016876,
|
| 619 |
+
"eval_runtime": 327.1397,
|
| 620 |
+
"eval_samples_per_second": 6.988,
|
| 621 |
+
"eval_steps_per_second": 0.874,
|
| 622 |
+
"eval_wer": 0.23395222750754438,
|
| 623 |
+
"step": 8200
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 21.32,
|
| 627 |
+
"learning_rate": 6.733657243816255e-05,
|
| 628 |
+
"loss": 0.0915,
|
| 629 |
+
"step": 8400
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 21.32,
|
| 633 |
+
"eval_loss": 0.3296717703342438,
|
| 634 |
+
"eval_runtime": 327.0362,
|
| 635 |
+
"eval_samples_per_second": 6.99,
|
| 636 |
+
"eval_steps_per_second": 0.875,
|
| 637 |
+
"eval_wer": 0.22832591683289857,
|
| 638 |
+
"step": 8400
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 21.83,
|
| 642 |
+
"learning_rate": 6.645318021201413e-05,
|
| 643 |
+
"loss": 0.0874,
|
| 644 |
+
"step": 8600
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 21.83,
|
| 648 |
+
"eval_loss": 0.3275238573551178,
|
| 649 |
+
"eval_runtime": 326.5367,
|
| 650 |
+
"eval_samples_per_second": 7.001,
|
| 651 |
+
"eval_steps_per_second": 0.876,
|
| 652 |
+
"eval_wer": 0.22945117896782774,
|
| 653 |
+
"step": 8600
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 22.33,
|
| 657 |
+
"learning_rate": 6.557420494699646e-05,
|
| 658 |
+
"loss": 0.0952,
|
| 659 |
+
"step": 8800
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 22.33,
|
| 663 |
+
"eval_loss": 0.34165430068969727,
|
| 664 |
+
"eval_runtime": 331.1514,
|
| 665 |
+
"eval_samples_per_second": 6.903,
|
| 666 |
+
"eval_steps_per_second": 0.864,
|
| 667 |
+
"eval_wer": 0.22796787888087566,
|
| 668 |
+
"step": 8800
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 22.84,
|
| 672 |
+
"learning_rate": 6.469081272084806e-05,
|
| 673 |
+
"loss": 0.0907,
|
| 674 |
+
"step": 9000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 22.84,
|
| 678 |
+
"eval_loss": 0.32556086778640747,
|
| 679 |
+
"eval_runtime": 330.5,
|
| 680 |
+
"eval_samples_per_second": 6.917,
|
| 681 |
+
"eval_steps_per_second": 0.865,
|
| 682 |
+
"eval_wer": 0.22858165822720067,
|
| 683 |
+
"step": 9000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 23.35,
|
| 687 |
+
"learning_rate": 6.380742049469966e-05,
|
| 688 |
+
"loss": 0.0807,
|
| 689 |
+
"step": 9200
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 23.35,
|
| 693 |
+
"eval_loss": 0.3502887785434723,
|
| 694 |
+
"eval_runtime": 336.4566,
|
| 695 |
+
"eval_samples_per_second": 6.794,
|
| 696 |
+
"eval_steps_per_second": 0.85,
|
| 697 |
+
"eval_wer": 0.2290419927369444,
|
| 698 |
+
"step": 9200
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 23.86,
|
| 702 |
+
"learning_rate": 6.292402826855123e-05,
|
| 703 |
+
"loss": 0.082,
|
| 704 |
+
"step": 9400
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 23.86,
|
| 708 |
+
"eval_loss": 0.344855934381485,
|
| 709 |
+
"eval_runtime": 339.6685,
|
| 710 |
+
"eval_samples_per_second": 6.73,
|
| 711 |
+
"eval_steps_per_second": 0.842,
|
| 712 |
+
"eval_wer": 0.2290419927369444,
|
| 713 |
+
"step": 9400
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 24.37,
|
| 717 |
+
"learning_rate": 6.204063604240284e-05,
|
| 718 |
+
"loss": 0.0801,
|
| 719 |
+
"step": 9600
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 24.37,
|
| 723 |
+
"eval_loss": 0.36849820613861084,
|
| 724 |
+
"eval_runtime": 338.3914,
|
| 725 |
+
"eval_samples_per_second": 6.755,
|
| 726 |
+
"eval_steps_per_second": 0.845,
|
| 727 |
+
"eval_wer": 0.22801902715973607,
|
| 728 |
+
"step": 9600
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 24.87,
|
| 732 |
+
"learning_rate": 6.115724381625441e-05,
|
| 733 |
+
"loss": 0.0755,
|
| 734 |
+
"step": 9800
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 24.87,
|
| 738 |
+
"eval_loss": 0.3435544967651367,
|
| 739 |
+
"eval_runtime": 337.5045,
|
| 740 |
+
"eval_samples_per_second": 6.773,
|
| 741 |
+
"eval_steps_per_second": 0.847,
|
| 742 |
+
"eval_wer": 0.22893969617922358,
|
| 743 |
+
"step": 9800
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 25.38,
|
| 747 |
+
"learning_rate": 6.027385159010601e-05,
|
| 748 |
+
"loss": 0.0735,
|
| 749 |
+
"step": 10000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 25.38,
|
| 753 |
+
"eval_loss": 0.3514951467514038,
|
| 754 |
+
"eval_runtime": 337.5311,
|
| 755 |
+
"eval_samples_per_second": 6.773,
|
| 756 |
+
"eval_steps_per_second": 0.847,
|
| 757 |
+
"eval_wer": 0.22766098920771316,
|
| 758 |
+
"step": 10000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 25.89,
|
| 762 |
+
"learning_rate": 5.93904593639576e-05,
|
| 763 |
+
"loss": 0.0749,
|
| 764 |
+
"step": 10200
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 25.89,
|
| 768 |
+
"eval_loss": 0.3425111174583435,
|
| 769 |
+
"eval_runtime": 341.8062,
|
| 770 |
+
"eval_samples_per_second": 6.688,
|
| 771 |
+
"eval_steps_per_second": 0.837,
|
| 772 |
+
"eval_wer": 0.22893969617922358,
|
| 773 |
+
"step": 10200
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 26.4,
|
| 777 |
+
"learning_rate": 5.850706713780919e-05,
|
| 778 |
+
"loss": 0.0756,
|
| 779 |
+
"step": 10400
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 26.4,
|
| 783 |
+
"eval_loss": 0.34799715876579285,
|
| 784 |
+
"eval_runtime": 327.2581,
|
| 785 |
+
"eval_samples_per_second": 6.985,
|
| 786 |
+
"eval_steps_per_second": 0.874,
|
| 787 |
+
"eval_wer": 0.22658687535164443,
|
| 788 |
+
"step": 10400
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 26.9,
|
| 792 |
+
"learning_rate": 5.7623674911660786e-05,
|
| 793 |
+
"loss": 0.0745,
|
| 794 |
+
"step": 10600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 26.9,
|
| 798 |
+
"eval_loss": 0.3655582368373871,
|
| 799 |
+
"eval_runtime": 327.7963,
|
| 800 |
+
"eval_samples_per_second": 6.974,
|
| 801 |
+
"eval_steps_per_second": 0.872,
|
| 802 |
+
"eval_wer": 0.2249501304281111,
|
| 803 |
+
"step": 10600
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 27.41,
|
| 807 |
+
"learning_rate": 5.674028268551237e-05,
|
| 808 |
+
"loss": 0.0739,
|
| 809 |
+
"step": 10800
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 27.41,
|
| 813 |
+
"eval_loss": 0.3493630588054657,
|
| 814 |
+
"eval_runtime": 325.9215,
|
| 815 |
+
"eval_samples_per_second": 7.014,
|
| 816 |
+
"eval_steps_per_second": 0.878,
|
| 817 |
+
"eval_wer": 0.23098562733364023,
|
| 818 |
+
"step": 10800
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 27.92,
|
| 822 |
+
"learning_rate": 5.585689045936396e-05,
|
| 823 |
+
"loss": 0.0747,
|
| 824 |
+
"step": 11000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 27.92,
|
| 828 |
+
"eval_loss": 0.3572988510131836,
|
| 829 |
+
"eval_runtime": 326.4765,
|
| 830 |
+
"eval_samples_per_second": 7.002,
|
| 831 |
+
"eval_steps_per_second": 0.876,
|
| 832 |
+
"eval_wer": 0.22541046493785485,
|
| 833 |
+
"step": 11000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 28.43,
|
| 837 |
+
"learning_rate": 5.49779151943463e-05,
|
| 838 |
+
"loss": 0.0638,
|
| 839 |
+
"step": 11200
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 28.43,
|
| 843 |
+
"eval_loss": 0.37718120217323303,
|
| 844 |
+
"eval_runtime": 326.7276,
|
| 845 |
+
"eval_samples_per_second": 6.997,
|
| 846 |
+
"eval_steps_per_second": 0.875,
|
| 847 |
+
"eval_wer": 0.22382486829318193,
|
| 848 |
+
"step": 11200
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 28.93,
|
| 852 |
+
"learning_rate": 5.409452296819788e-05,
|
| 853 |
+
"loss": 0.0692,
|
| 854 |
+
"step": 11400
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 28.93,
|
| 858 |
+
"eval_loss": 0.3608773648738861,
|
| 859 |
+
"eval_runtime": 327.8617,
|
| 860 |
+
"eval_samples_per_second": 6.972,
|
| 861 |
+
"eval_steps_per_second": 0.872,
|
| 862 |
+
"eval_wer": 0.227763285765434,
|
| 863 |
+
"step": 11400
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 29.44,
|
| 867 |
+
"learning_rate": 5.321113074204947e-05,
|
| 868 |
+
"loss": 0.0628,
|
| 869 |
+
"step": 11600
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 29.44,
|
| 873 |
+
"eval_loss": 0.3680490553379059,
|
| 874 |
+
"eval_runtime": 328.0778,
|
| 875 |
+
"eval_samples_per_second": 6.968,
|
| 876 |
+
"eval_steps_per_second": 0.872,
|
| 877 |
+
"eval_wer": 0.2249501304281111,
|
| 878 |
+
"step": 11600
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 29.95,
|
| 882 |
+
"learning_rate": 5.232773851590106e-05,
|
| 883 |
+
"loss": 0.0639,
|
| 884 |
+
"step": 11800
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 29.95,
|
| 888 |
+
"eval_loss": 0.3743281364440918,
|
| 889 |
+
"eval_runtime": 334.0745,
|
| 890 |
+
"eval_samples_per_second": 6.843,
|
| 891 |
+
"eval_steps_per_second": 0.856,
|
| 892 |
+
"eval_wer": 0.22541046493785485,
|
| 893 |
+
"step": 11800
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 30.46,
|
| 897 |
+
"learning_rate": 5.1444346289752655e-05,
|
| 898 |
+
"loss": 0.067,
|
| 899 |
+
"step": 12000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 30.46,
|
| 903 |
+
"eval_loss": 0.370677649974823,
|
| 904 |
+
"eval_runtime": 334.479,
|
| 905 |
+
"eval_samples_per_second": 6.835,
|
| 906 |
+
"eval_steps_per_second": 0.855,
|
| 907 |
+
"eval_wer": 0.22397831312976318,
|
| 908 |
+
"step": 12000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 30.96,
|
| 912 |
+
"learning_rate": 5.056095406360424e-05,
|
| 913 |
+
"loss": 0.0586,
|
| 914 |
+
"step": 12200
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 30.96,
|
| 918 |
+
"eval_loss": 0.3863554298877716,
|
| 919 |
+
"eval_runtime": 334.1121,
|
| 920 |
+
"eval_samples_per_second": 6.842,
|
| 921 |
+
"eval_steps_per_second": 0.856,
|
| 922 |
+
"eval_wer": 0.22413175796634444,
|
| 923 |
+
"step": 12200
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 31.47,
|
| 927 |
+
"learning_rate": 4.967756183745583e-05,
|
| 928 |
+
"loss": 0.0601,
|
| 929 |
+
"step": 12400
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 31.47,
|
| 933 |
+
"eval_loss": 0.3715435266494751,
|
| 934 |
+
"eval_runtime": 337.8795,
|
| 935 |
+
"eval_samples_per_second": 6.766,
|
| 936 |
+
"eval_steps_per_second": 0.846,
|
| 937 |
+
"eval_wer": 0.22633113395734233,
|
| 938 |
+
"step": 12400
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 31.98,
|
| 942 |
+
"learning_rate": 4.8798586572438167e-05,
|
| 943 |
+
"loss": 0.0607,
|
| 944 |
+
"step": 12600
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 31.98,
|
| 948 |
+
"eval_loss": 0.36769574880599976,
|
| 949 |
+
"eval_runtime": 335.2748,
|
| 950 |
+
"eval_samples_per_second": 6.818,
|
| 951 |
+
"eval_steps_per_second": 0.853,
|
| 952 |
+
"eval_wer": 0.22566620633215692,
|
| 953 |
+
"step": 12600
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 32.49,
|
| 957 |
+
"learning_rate": 4.791519434628976e-05,
|
| 958 |
+
"loss": 0.0585,
|
| 959 |
+
"step": 12800
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 32.49,
|
| 963 |
+
"eval_loss": 0.38456135988235474,
|
| 964 |
+
"eval_runtime": 335.5304,
|
| 965 |
+
"eval_samples_per_second": 6.813,
|
| 966 |
+
"eval_steps_per_second": 0.852,
|
| 967 |
+
"eval_wer": 0.22607539256304027,
|
| 968 |
+
"step": 12800
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 32.99,
|
| 972 |
+
"learning_rate": 4.703180212014134e-05,
|
| 973 |
+
"loss": 0.0549,
|
| 974 |
+
"step": 13000
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 32.99,
|
| 978 |
+
"eval_loss": 0.376272976398468,
|
| 979 |
+
"eval_runtime": 339.7138,
|
| 980 |
+
"eval_samples_per_second": 6.729,
|
| 981 |
+
"eval_steps_per_second": 0.842,
|
| 982 |
+
"eval_wer": 0.22883739962150274,
|
| 983 |
+
"step": 13000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 33.5,
|
| 987 |
+
"learning_rate": 4.614840989399293e-05,
|
| 988 |
+
"loss": 0.0566,
|
| 989 |
+
"step": 13200
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 33.5,
|
| 993 |
+
"eval_loss": 0.375703901052475,
|
| 994 |
+
"eval_runtime": 340.809,
|
| 995 |
+
"eval_samples_per_second": 6.708,
|
| 996 |
+
"eval_steps_per_second": 0.839,
|
| 997 |
+
"eval_wer": 0.22551276149557567,
|
| 998 |
+
"step": 13200
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 34.01,
|
| 1002 |
+
"learning_rate": 4.5265017667844524e-05,
|
| 1003 |
+
"loss": 0.0601,
|
| 1004 |
+
"step": 13400
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 34.01,
|
| 1008 |
+
"eval_loss": 0.3690040707588196,
|
| 1009 |
+
"eval_runtime": 340.0174,
|
| 1010 |
+
"eval_samples_per_second": 6.723,
|
| 1011 |
+
"eval_steps_per_second": 0.841,
|
| 1012 |
+
"eval_wer": 0.2242852028029257,
|
| 1013 |
+
"step": 13400
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 34.52,
|
| 1017 |
+
"learning_rate": 4.4381625441696115e-05,
|
| 1018 |
+
"loss": 0.0644,
|
| 1019 |
+
"step": 13600
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 34.52,
|
| 1023 |
+
"eval_loss": 0.38989028334617615,
|
| 1024 |
+
"eval_runtime": 330.5652,
|
| 1025 |
+
"eval_samples_per_second": 6.915,
|
| 1026 |
+
"eval_steps_per_second": 0.865,
|
| 1027 |
+
"eval_wer": 0.22801902715973607,
|
| 1028 |
+
"step": 13600
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 35.03,
|
| 1032 |
+
"learning_rate": 4.3498233215547706e-05,
|
| 1033 |
+
"loss": 0.0534,
|
| 1034 |
+
"step": 13800
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 35.03,
|
| 1038 |
+
"eval_loss": 0.3764423429965973,
|
| 1039 |
+
"eval_runtime": 331.0495,
|
| 1040 |
+
"eval_samples_per_second": 6.905,
|
| 1041 |
+
"eval_steps_per_second": 0.864,
|
| 1042 |
+
"eval_wer": 0.22643343051506318,
|
| 1043 |
+
"step": 13800
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 35.53,
|
| 1047 |
+
"learning_rate": 4.26148409893993e-05,
|
| 1048 |
+
"loss": 0.0533,
|
| 1049 |
+
"step": 14000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 35.53,
|
| 1053 |
+
"eval_loss": 0.39295488595962524,
|
| 1054 |
+
"eval_runtime": 324.4991,
|
| 1055 |
+
"eval_samples_per_second": 7.045,
|
| 1056 |
+
"eval_steps_per_second": 0.881,
|
| 1057 |
+
"eval_wer": 0.2250012787069715,
|
| 1058 |
+
"step": 14000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 36.04,
|
| 1062 |
+
"learning_rate": 4.173144876325089e-05,
|
| 1063 |
+
"loss": 0.0538,
|
| 1064 |
+
"step": 14200
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 36.04,
|
| 1068 |
+
"eval_loss": 0.3971385061740875,
|
| 1069 |
+
"eval_runtime": 324.5617,
|
| 1070 |
+
"eval_samples_per_second": 7.043,
|
| 1071 |
+
"eval_steps_per_second": 0.881,
|
| 1072 |
+
"eval_wer": 0.22423405452406525,
|
| 1073 |
+
"step": 14200
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 36.55,
|
| 1077 |
+
"learning_rate": 4.084805653710247e-05,
|
| 1078 |
+
"loss": 0.0549,
|
| 1079 |
+
"step": 14400
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 36.55,
|
| 1083 |
+
"eval_loss": 0.41013625264167786,
|
| 1084 |
+
"eval_runtime": 327.8225,
|
| 1085 |
+
"eval_samples_per_second": 6.973,
|
| 1086 |
+
"eval_steps_per_second": 0.872,
|
| 1087 |
+
"eval_wer": 0.22766098920771316,
|
| 1088 |
+
"step": 14400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 37.06,
|
| 1092 |
+
"learning_rate": 3.9964664310954064e-05,
|
| 1093 |
+
"loss": 0.0558,
|
| 1094 |
+
"step": 14600
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 37.06,
|
| 1098 |
+
"eval_loss": 0.3944765031337738,
|
| 1099 |
+
"eval_runtime": 329.1988,
|
| 1100 |
+
"eval_samples_per_second": 6.944,
|
| 1101 |
+
"eval_steps_per_second": 0.869,
|
| 1102 |
+
"eval_wer": 0.22408060968748403,
|
| 1103 |
+
"step": 14600
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 37.56,
|
| 1107 |
+
"learning_rate": 3.9081272084805655e-05,
|
| 1108 |
+
"loss": 0.0592,
|
| 1109 |
+
"step": 14800
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 37.56,
|
| 1113 |
+
"eval_loss": 0.4027334451675415,
|
| 1114 |
+
"eval_runtime": 325.5906,
|
| 1115 |
+
"eval_samples_per_second": 7.021,
|
| 1116 |
+
"eval_steps_per_second": 0.878,
|
| 1117 |
+
"eval_wer": 0.2249501304281111,
|
| 1118 |
+
"step": 14800
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 28.52,
|
| 1122 |
+
"learning_rate": 5.421465968586388e-05,
|
| 1123 |
+
"loss": 0.125,
|
| 1124 |
+
"step": 15000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 28.52,
|
| 1128 |
+
"eval_loss": 0.310897558927536,
|
| 1129 |
+
"eval_runtime": 158.8811,
|
| 1130 |
+
"eval_samples_per_second": 7.282,
|
| 1131 |
+
"eval_steps_per_second": 0.913,
|
| 1132 |
+
"eval_wer": 0.1662258953168044,
|
| 1133 |
+
"step": 15000
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 28.9,
|
| 1137 |
+
"learning_rate": 5.3560209424083776e-05,
|
| 1138 |
+
"loss": 0.1162,
|
| 1139 |
+
"step": 15200
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 28.9,
|
| 1143 |
+
"eval_loss": 0.2863084673881531,
|
| 1144 |
+
"eval_runtime": 159.2387,
|
| 1145 |
+
"eval_samples_per_second": 7.266,
|
| 1146 |
+
"eval_steps_per_second": 0.911,
|
| 1147 |
+
"eval_wer": 0.16831955922865013,
|
| 1148 |
+
"step": 15200
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 29.28,
|
| 1152 |
+
"learning_rate": 5.290575916230367e-05,
|
| 1153 |
+
"loss": 0.1021,
|
| 1154 |
+
"step": 15400
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 29.28,
|
| 1158 |
+
"eval_loss": 0.2973718047142029,
|
| 1159 |
+
"eval_runtime": 159.1999,
|
| 1160 |
+
"eval_samples_per_second": 7.268,
|
| 1161 |
+
"eval_steps_per_second": 0.911,
|
| 1162 |
+
"eval_wer": 0.16815426997245178,
|
| 1163 |
+
"step": 15400
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 29.66,
|
| 1167 |
+
"learning_rate": 5.225130890052357e-05,
|
| 1168 |
+
"loss": 0.1019,
|
| 1169 |
+
"step": 15600
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 29.66,
|
| 1173 |
+
"eval_loss": 0.2894442677497864,
|
| 1174 |
+
"eval_runtime": 161.3136,
|
| 1175 |
+
"eval_samples_per_second": 7.172,
|
| 1176 |
+
"eval_steps_per_second": 0.899,
|
| 1177 |
+
"eval_wer": 0.16820936639118458,
|
| 1178 |
+
"step": 15600
|
| 1179 |
+
}
|
| 1180 |
+
],
|
| 1181 |
+
"max_steps": 31560,
|
| 1182 |
+
"num_train_epochs": 60,
|
| 1183 |
+
"total_flos": 6.589332771620831e+19,
|
| 1184 |
+
"trial_name": null,
|
| 1185 |
+
"trial_params": null
|
| 1186 |
+
}
|