Commit
•
699e2d9
1
Parent(s):
6f1fee3
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.005671739578247,
|
| 4 |
+
"eval_runtime": 2689.3966,
|
| 5 |
+
"eval_samples_per_second": 1.885,
|
| 6 |
+
"eval_steps_per_second": 0.471,
|
| 7 |
+
"eval_wer": 27.269551195915078,
|
| 8 |
+
"train_loss": 1.167057704925537,
|
| 9 |
+
"train_runtime": 5685.0642,
|
| 10 |
+
"train_samples_per_second": 0.225,
|
| 11 |
+
"train_steps_per_second": 0.004
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.005671739578247,
|
| 4 |
+
"eval_runtime": 2689.3966,
|
| 5 |
+
"eval_samples_per_second": 1.885,
|
| 6 |
+
"eval_steps_per_second": 0.471,
|
| 7 |
+
"eval_wer": 27.269551195915078
|
| 8 |
+
}
|
runs/Dec08_11-57-22_129-213-148-34/events.out.tfevents.1670509305.129-213-148-34.128289.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e6d0a5f412aef7ed714dca4e29e59b2ecd238fa993fbfdd75a5147779b6679e
|
| 3 |
+
size 352
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.167057704925537,
|
| 4 |
+
"train_runtime": 5685.0642,
|
| 5 |
+
"train_samples_per_second": 0.225,
|
| 6 |
+
"train_steps_per_second": 0.004
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 20,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"eval_loss": 1.02778160572052,
|
| 13 |
+
"eval_runtime": 2648.1583,
|
| 14 |
+
"eval_samples_per_second": 1.914,
|
| 15 |
+
"eval_steps_per_second": 0.479,
|
| 16 |
+
"eval_wer": 36.656812684762166,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 1.005671739578247,
|
| 22 |
+
"eval_runtime": 2678.7989,
|
| 23 |
+
"eval_samples_per_second": 1.892,
|
| 24 |
+
"eval_steps_per_second": 0.473,
|
| 25 |
+
"eval_wer": 27.269551195915078,
|
| 26 |
+
"step": 20
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"step": 20,
|
| 31 |
+
"total_flos": 2.717658906624e+18,
|
| 32 |
+
"train_loss": 1.167057704925537,
|
| 33 |
+
"train_runtime": 5685.0642,
|
| 34 |
+
"train_samples_per_second": 0.225,
|
| 35 |
+
"train_steps_per_second": 0.004
|
| 36 |
+
}
|
| 37 |
+
],
|
| 38 |
+
"max_steps": 20,
|
| 39 |
+
"num_train_epochs": 9223372036854775807,
|
| 40 |
+
"total_flos": 2.717658906624e+18,
|
| 41 |
+
"trial_name": null,
|
| 42 |
+
"trial_params": null
|
| 43 |
+
}
|