Commit
•
3108cfd
1
Parent(s):
a85f1ff
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Jun15_16-09-17_labgpu/events.out.tfevents.1655310262.labgpu.23398.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +31 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6678700361010831,
|
| 4 |
+
"eval_loss": 0.8396075367927551,
|
| 5 |
+
"eval_runtime": 1.6845,
|
| 6 |
+
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 164.444,
|
| 8 |
+
"eval_steps_per_second": 20.778,
|
| 9 |
+
"train_loss": 60928.27408236968,
|
| 10 |
+
"train_runtime": 290.1511,
|
| 11 |
+
"train_samples": 2490,
|
| 12 |
+
"train_samples_per_second": 85.817,
|
| 13 |
+
"train_steps_per_second": 2.688
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6678700361010831,
|
| 4 |
+
"eval_loss": 0.8396075367927551,
|
| 5 |
+
"eval_runtime": 1.6845,
|
| 6 |
+
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 164.444,
|
| 8 |
+
"eval_steps_per_second": 20.778
|
| 9 |
+
}
|
runs/Jun15_16-09-17_labgpu/events.out.tfevents.1655310262.labgpu.23398.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d97c55896865cc2310e74c1419d904d6fe92434ed2fb5174125a2b2801840ae0
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 60928.27408236968,
|
| 4 |
+
"train_runtime": 290.1511,
|
| 5 |
+
"train_samples": 2490,
|
| 6 |
+
"train_samples_per_second": 85.817,
|
| 7 |
+
"train_steps_per_second": 2.688
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 780,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 6.41,
|
| 12 |
+
"learning_rate": 1.076923076923077e-05,
|
| 13 |
+
"loss": 95047.952,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 10.0,
|
| 18 |
+
"step": 780,
|
| 19 |
+
"total_flos": 390360542976000.0,
|
| 20 |
+
"train_loss": 60928.27408236968,
|
| 21 |
+
"train_runtime": 290.1511,
|
| 22 |
+
"train_samples_per_second": 85.817,
|
| 23 |
+
"train_steps_per_second": 2.688
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"max_steps": 780,
|
| 27 |
+
"num_train_epochs": 10,
|
| 28 |
+
"total_flos": 390360542976000.0,
|
| 29 |
+
"trial_name": null,
|
| 30 |
+
"trial_params": null
|
| 31 |
+
}
|