End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Oct23_22-48-20_hieu-pc/events.out.tfevents.1666540758.hieu-pc.904098.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +34 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.96,
|
| 3 |
+
"eval_loss": 3.4788997173309326,
|
| 4 |
+
"eval_runtime": 8.5263,
|
| 5 |
+
"eval_samples": 198,
|
| 6 |
+
"eval_samples_per_second": 23.222,
|
| 7 |
+
"eval_steps_per_second": 2.932,
|
| 8 |
+
"eval_wer": 1.0,
|
| 9 |
+
"train_loss": 11.506034655448717,
|
| 10 |
+
"train_runtime": 418.5836,
|
| 11 |
+
"train_samples": 421,
|
| 12 |
+
"train_samples_per_second": 15.087,
|
| 13 |
+
"train_steps_per_second": 0.466
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.96,
|
| 3 |
+
"eval_loss": 3.4788997173309326,
|
| 4 |
+
"eval_runtime": 8.5263,
|
| 5 |
+
"eval_samples": 198,
|
| 6 |
+
"eval_samples_per_second": 23.222,
|
| 7 |
+
"eval_steps_per_second": 2.932,
|
| 8 |
+
"eval_wer": 1.0
|
| 9 |
+
}
|
runs/Oct23_22-48-20_hieu-pc/events.out.tfevents.1666540758.hieu-pc.904098.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e66b100f5cef5e0901401d8cd323ddd4733a1c3365ce53e2ba298455b0baa55a
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.96,
|
| 3 |
+
"train_loss": 11.506034655448717,
|
| 4 |
+
"train_runtime": 418.5836,
|
| 5 |
+
"train_samples": 421,
|
| 6 |
+
"train_samples_per_second": 15.087,
|
| 7 |
+
"train_steps_per_second": 0.466
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.962962962962964,
|
| 5 |
+
"global_step": 195,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 7.67,
|
| 12 |
+
"eval_loss": 6.002369403839111,
|
| 13 |
+
"eval_runtime": 8.8066,
|
| 14 |
+
"eval_samples_per_second": 22.483,
|
| 15 |
+
"eval_steps_per_second": 2.839,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 14.96,
|
| 21 |
+
"step": 195,
|
| 22 |
+
"total_flos": 8.135466484187405e+17,
|
| 23 |
+
"train_loss": 11.506034655448717,
|
| 24 |
+
"train_runtime": 418.5836,
|
| 25 |
+
"train_samples_per_second": 15.087,
|
| 26 |
+
"train_steps_per_second": 0.466
|
| 27 |
+
}
|
| 28 |
+
],
|
| 29 |
+
"max_steps": 195,
|
| 30 |
+
"num_train_epochs": 15,
|
| 31 |
+
"total_flos": 8.135466484187405e+17,
|
| 32 |
+
"trial_name": null,
|
| 33 |
+
"trial_params": null
|
| 34 |
+
}
|