End of training
Browse files- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.5286828336634978,
|
| 4 |
+
"eval_loss": 2.1286187171936035,
|
| 5 |
+
"eval_runtime": 940.5495,
|
| 6 |
+
"eval_samples": 844024,
|
| 7 |
+
"eval_samples_per_second": 897.373,
|
| 8 |
+
"eval_steps_per_second": 7.011,
|
| 9 |
+
"total_flos": 9.242888597926871e+18,
|
| 10 |
+
"train_loss": 2.4459246747957275,
|
| 11 |
+
"train_runtime": 102710.4528,
|
| 12 |
+
"train_samples": 3376092,
|
| 13 |
+
"train_samples_per_second": 328.7,
|
| 14 |
+
"train_steps_per_second": 2.568
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.5286828336634978,
|
| 4 |
+
"eval_loss": 2.1286187171936035,
|
| 5 |
+
"eval_runtime": 940.5495,
|
| 6 |
+
"eval_samples": 844024,
|
| 7 |
+
"eval_samples_per_second": 897.373,
|
| 8 |
+
"eval_steps_per_second": 7.011
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 9.242888597926871e+18,
|
| 4 |
+
"train_loss": 2.4459246747957275,
|
| 5 |
+
"train_runtime": 102710.4528,
|
| 6 |
+
"train_samples": 3376092,
|
| 7 |
+
"train_samples_per_second": 328.7,
|
| 8 |
+
"train_steps_per_second": 2.568
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|