Commit
•
2e11062
1
Parent(s):
5c3592c
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Feb01_13-54-29_brutasse/events.out.tfevents.1643725033.brutasse.6102.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +52 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.1171964406967163,
|
| 4 |
+
"eval_runtime": 71.673,
|
| 5 |
+
"eval_samples": 1781,
|
| 6 |
+
"eval_samples_per_second": 24.849,
|
| 7 |
+
"eval_steps_per_second": 3.111,
|
| 8 |
+
"eval_wer": 1.007025432064072,
|
| 9 |
+
"train_loss": 5.89979406669315,
|
| 10 |
+
"train_runtime": 748.1359,
|
| 11 |
+
"train_samples": 3788,
|
| 12 |
+
"train_samples_per_second": 15.19,
|
| 13 |
+
"train_steps_per_second": 0.473
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.1171964406967163,
|
| 4 |
+
"eval_runtime": 71.673,
|
| 5 |
+
"eval_samples": 1781,
|
| 6 |
+
"eval_samples_per_second": 24.849,
|
| 7 |
+
"eval_steps_per_second": 3.111,
|
| 8 |
+
"eval_wer": 1.007025432064072
|
| 9 |
+
}
|
runs/Feb01_13-54-29_brutasse/events.out.tfevents.1643725033.brutasse.6102.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9396da1ebf1d7d8981f964e9c6972d5ead18227a50e469eeb5296e421109ec22
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 5.89979406669315,
|
| 4 |
+
"train_runtime": 748.1359,
|
| 5 |
+
"train_samples": 3788,
|
| 6 |
+
"train_samples_per_second": 15.19,
|
| 7 |
+
"train_steps_per_second": 0.473
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9957805907173,
|
| 5 |
+
"global_step": 354,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.84,
|
| 12 |
+
"eval_loss": 4.014804363250732,
|
| 13 |
+
"eval_runtime": 71.3844,
|
| 14 |
+
"eval_samples_per_second": 24.949,
|
| 15 |
+
"eval_steps_per_second": 3.124,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.69,
|
| 21 |
+
"eval_loss": 3.1738100051879883,
|
| 22 |
+
"eval_runtime": 71.3843,
|
| 23 |
+
"eval_samples_per_second": 24.949,
|
| 24 |
+
"eval_steps_per_second": 3.124,
|
| 25 |
+
"eval_wer": 1.0,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.54,
|
| 30 |
+
"eval_loss": 2.5980231761932373,
|
| 31 |
+
"eval_runtime": 71.3516,
|
| 32 |
+
"eval_samples_per_second": 24.961,
|
| 33 |
+
"eval_steps_per_second": 3.125,
|
| 34 |
+
"eval_wer": 1.0236054517352817,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"step": 354,
|
| 40 |
+
"total_flos": 1.5058464259703962e+18,
|
| 41 |
+
"train_loss": 5.89979406669315,
|
| 42 |
+
"train_runtime": 748.1359,
|
| 43 |
+
"train_samples_per_second": 15.19,
|
| 44 |
+
"train_steps_per_second": 0.473
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"max_steps": 354,
|
| 48 |
+
"num_train_epochs": 3,
|
| 49 |
+
"total_flos": 1.5058464259703962e+18,
|
| 50 |
+
"trial_name": null,
|
| 51 |
+
"trial_params": null
|
| 52 |
+
}
|