End of training
Browse files- all_results.json +21 -0
- eval_results.json +16 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"epoch_mm": 10.0,
|
| 4 |
+
"eval_accuracy": 0.8618441161487519,
|
| 5 |
+
"eval_accuracy_mm": 0.8657445077298617,
|
| 6 |
+
"eval_loss": 0.3644271194934845,
|
| 7 |
+
"eval_loss_mm": 0.3617265522480011,
|
| 8 |
+
"eval_runtime": 27.5384,
|
| 9 |
+
"eval_runtime_mm": 27.7514,
|
| 10 |
+
"eval_samples": 9815,
|
| 11 |
+
"eval_samples_mm": 9832,
|
| 12 |
+
"eval_samples_per_second": 356.411,
|
| 13 |
+
"eval_samples_per_second_mm": 354.289,
|
| 14 |
+
"eval_steps_per_second": 44.556,
|
| 15 |
+
"eval_steps_per_second_mm": 44.286,
|
| 16 |
+
"train_loss": 0.20378830649706656,
|
| 17 |
+
"train_runtime": 61814.3836,
|
| 18 |
+
"train_samples": 392702,
|
| 19 |
+
"train_samples_per_second": 63.529,
|
| 20 |
+
"train_steps_per_second": 3.971
|
| 21 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"epoch_mm": 10.0,
|
| 4 |
+
"eval_accuracy": 0.8618441161487519,
|
| 5 |
+
"eval_accuracy_mm": 0.8657445077298617,
|
| 6 |
+
"eval_loss": 0.3644271194934845,
|
| 7 |
+
"eval_loss_mm": 0.3617265522480011,
|
| 8 |
+
"eval_runtime": 27.5384,
|
| 9 |
+
"eval_runtime_mm": 27.7514,
|
| 10 |
+
"eval_samples": 9815,
|
| 11 |
+
"eval_samples_mm": 9832,
|
| 12 |
+
"eval_samples_per_second": 356.411,
|
| 13 |
+
"eval_samples_per_second_mm": 354.289,
|
| 14 |
+
"eval_steps_per_second": 44.556,
|
| 15 |
+
"eval_steps_per_second_mm": 44.286
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.20378830649706656,
|
| 4 |
+
"train_runtime": 61814.3836,
|
| 5 |
+
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 63.529,
|
| 7 |
+
"train_steps_per_second": 3.971
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|