End of training
Browse files- all_results.json +28 -0
- runs/Nov27_06-11-08_421428218b1b/events.out.tfevents.1669551405.421428218b1b.106.2 +3 -0
- test_results.json +11 -0
- train_more_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- valid_results.json +11 -0
all_results.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.8176672128705497,
|
| 4 |
+
"eval_f1": 0.8067463077825504,
|
| 5 |
+
"eval_loss": 0.7063722014427185,
|
| 6 |
+
"eval_precision": 0.808932447502446,
|
| 7 |
+
"eval_recall": 0.8176672128705497,
|
| 8 |
+
"eval_runtime": 100.5004,
|
| 9 |
+
"eval_samples_per_second": 267.183,
|
| 10 |
+
"eval_steps_per_second": 4.179,
|
| 11 |
+
"test_accuracy": 0.8172575599582899,
|
| 12 |
+
"test_f1": 0.8057061753323418,
|
| 13 |
+
"test_loss": 0.7021384835243225,
|
| 14 |
+
"test_precision": 0.8093542627058361,
|
| 15 |
+
"test_recall": 0.8172575599582899,
|
| 16 |
+
"test_runtime": 100.0753,
|
| 17 |
+
"test_samples_per_second": 268.318,
|
| 18 |
+
"test_steps_per_second": 4.197,
|
| 19 |
+
"total_flos": 8.179980758810437e+19,
|
| 20 |
+
"train_accuracy": 0.8244604584473866,
|
| 21 |
+
"train_f1": 0.8143373319248239,
|
| 22 |
+
"train_loss": 0.6935074329376221,
|
| 23 |
+
"train_precision": 0.8209253030287482,
|
| 24 |
+
"train_recall": 0.8244604584473866,
|
| 25 |
+
"train_runtime": 847.887,
|
| 26 |
+
"train_samples_per_second": 253.35,
|
| 27 |
+
"train_steps_per_second": 3.959
|
| 28 |
+
}
|
runs/Nov27_06-11-08_421428218b1b/events.out.tfevents.1669551405.421428218b1b.106.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce8349c83b581dc98b31a31078f08ad4cf6633e704cdefce358cd8893f6d13fe
|
| 3 |
+
size 1456
|
test_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"test_accuracy": 0.8172575599582899,
|
| 4 |
+
"test_f1": 0.8057061753323418,
|
| 5 |
+
"test_loss": 0.7021384835243225,
|
| 6 |
+
"test_precision": 0.8093542627058361,
|
| 7 |
+
"test_recall": 0.8172575599582899,
|
| 8 |
+
"test_runtime": 100.0753,
|
| 9 |
+
"test_samples_per_second": 268.318,
|
| 10 |
+
"test_steps_per_second": 4.197
|
| 11 |
+
}
|
train_more_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_accuracy": 0.8244604584473866,
|
| 4 |
+
"train_f1": 0.8143373319248239,
|
| 5 |
+
"train_loss": 0.6935074329376221,
|
| 6 |
+
"train_precision": 0.8209253030287482,
|
| 7 |
+
"train_recall": 0.8244604584473866,
|
| 8 |
+
"train_runtime": 847.887,
|
| 9 |
+
"train_samples_per_second": 253.35,
|
| 10 |
+
"train_steps_per_second": 3.959
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 8.179980758810437e+19,
|
| 4 |
+
"train_loss": 1.7412154973476806,
|
| 5 |
+
"train_runtime": 20817.4419,
|
| 6 |
+
"train_samples_per_second": 154.783,
|
| 7 |
+
"train_steps_per_second": 0.605
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
valid_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.8176672128705497,
|
| 4 |
+
"eval_f1": 0.8067463077825504,
|
| 5 |
+
"eval_loss": 0.7063722014427185,
|
| 6 |
+
"eval_precision": 0.808932447502446,
|
| 7 |
+
"eval_recall": 0.8176672128705497,
|
| 8 |
+
"eval_runtime": 100.5004,
|
| 9 |
+
"eval_samples_per_second": 267.183,
|
| 10 |
+
"eval_steps_per_second": 4.179
|
| 11 |
+
}
|