End of training
Browse files- all_results.json +28 -0
- eval_results.json +13 -0
- generated_predictions.txt +0 -0
- predict_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +1046 -0
all_results.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.0,
|
| 3 |
+
"eval_gen_len": 45.94139194139194,
|
| 4 |
+
"eval_loss": 2.0570528507232666,
|
| 5 |
+
"eval_rouge1": 33.0932,
|
| 6 |
+
"eval_rouge2": 14.9633,
|
| 7 |
+
"eval_rougeL": 28.6426,
|
| 8 |
+
"eval_rougeLsum": 30.8639,
|
| 9 |
+
"eval_runtime": 69.1967,
|
| 10 |
+
"eval_samples": 819,
|
| 11 |
+
"eval_samples_per_second": 11.836,
|
| 12 |
+
"eval_steps_per_second": 0.751,
|
| 13 |
+
"predict_gen_len": 45.05230769230769,
|
| 14 |
+
"predict_loss": 2.070528030395508,
|
| 15 |
+
"predict_rouge1": 33.1232,
|
| 16 |
+
"predict_rouge2": 14.9087,
|
| 17 |
+
"predict_rougeL": 28.6061,
|
| 18 |
+
"predict_rougeLsum": 30.7046,
|
| 19 |
+
"predict_runtime": 102.9053,
|
| 20 |
+
"predict_samples": 1300,
|
| 21 |
+
"predict_samples_per_second": 12.633,
|
| 22 |
+
"predict_steps_per_second": 0.797,
|
| 23 |
+
"train_loss": 2.4905450729393737,
|
| 24 |
+
"train_runtime": 8327.4677,
|
| 25 |
+
"train_samples": 10874,
|
| 26 |
+
"train_samples_per_second": 26.116,
|
| 27 |
+
"train_steps_per_second": 0.408
|
| 28 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.0,
|
| 3 |
+
"eval_gen_len": 45.94139194139194,
|
| 4 |
+
"eval_loss": 2.0570528507232666,
|
| 5 |
+
"eval_rouge1": 33.0932,
|
| 6 |
+
"eval_rouge2": 14.9633,
|
| 7 |
+
"eval_rougeL": 28.6426,
|
| 8 |
+
"eval_rougeLsum": 30.8639,
|
| 9 |
+
"eval_runtime": 69.1967,
|
| 10 |
+
"eval_samples": 819,
|
| 11 |
+
"eval_samples_per_second": 11.836,
|
| 12 |
+
"eval_steps_per_second": 0.751
|
| 13 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
predict_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_gen_len": 45.05230769230769,
|
| 3 |
+
"predict_loss": 2.070528030395508,
|
| 4 |
+
"predict_rouge1": 33.1232,
|
| 5 |
+
"predict_rouge2": 14.9087,
|
| 6 |
+
"predict_rougeL": 28.6061,
|
| 7 |
+
"predict_rougeLsum": 30.7046,
|
| 8 |
+
"predict_runtime": 102.9053,
|
| 9 |
+
"predict_samples": 1300,
|
| 10 |
+
"predict_samples_per_second": 12.633,
|
| 11 |
+
"predict_steps_per_second": 0.797
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.0,
|
| 3 |
+
"train_loss": 2.4905450729393737,
|
| 4 |
+
"train_runtime": 8327.4677,
|
| 5 |
+
"train_samples": 10874,
|
| 6 |
+
"train_samples_per_second": 26.116,
|
| 7 |
+
"train_steps_per_second": 0.408
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1046 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.0570528507232666,
|
| 3 |
+
"best_model_checkpoint": "t5-base-snl/checkpoint-2890",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"global_step": 3230,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 4.9632352941176476e-05,
|
| 13 |
+
"loss": 4.9792,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.29,
|
| 18 |
+
"learning_rate": 4.9264705882352944e-05,
|
| 19 |
+
"loss": 3.7166,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.44,
|
| 24 |
+
"learning_rate": 4.889705882352941e-05,
|
| 25 |
+
"loss": 3.2528,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.59,
|
| 30 |
+
"learning_rate": 4.8529411764705885e-05,
|
| 31 |
+
"loss": 3.0823,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.74,
|
| 36 |
+
"learning_rate": 4.816176470588236e-05,
|
| 37 |
+
"loss": 3.0381,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.88,
|
| 42 |
+
"learning_rate": 4.7794117647058826e-05,
|
| 43 |
+
"loss": 2.9943,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_gen_len": 18.976800976800977,
|
| 49 |
+
"eval_loss": 2.2042253017425537,
|
| 50 |
+
"eval_rouge1": 28.1135,
|
| 51 |
+
"eval_rouge2": 13.7477,
|
| 52 |
+
"eval_rougeL": 25.4842,
|
| 53 |
+
"eval_rougeLsum": 26.6467,
|
| 54 |
+
"eval_runtime": 22.885,
|
| 55 |
+
"eval_samples_per_second": 35.788,
|
| 56 |
+
"eval_steps_per_second": 2.272,
|
| 57 |
+
"step": 170
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.03,
|
| 61 |
+
"learning_rate": 4.742647058823529e-05,
|
| 62 |
+
"loss": 2.9188,
|
| 63 |
+
"step": 175
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.18,
|
| 67 |
+
"learning_rate": 4.705882352941177e-05,
|
| 68 |
+
"loss": 2.8824,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.32,
|
| 73 |
+
"learning_rate": 4.669117647058824e-05,
|
| 74 |
+
"loss": 2.8751,
|
| 75 |
+
"step": 225
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.47,
|
| 79 |
+
"learning_rate": 4.632352941176471e-05,
|
| 80 |
+
"loss": 2.8037,
|
| 81 |
+
"step": 250
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.62,
|
| 85 |
+
"learning_rate": 4.5955882352941176e-05,
|
| 86 |
+
"loss": 2.7824,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.76,
|
| 91 |
+
"learning_rate": 4.558823529411765e-05,
|
| 92 |
+
"loss": 2.7789,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.91,
|
| 97 |
+
"learning_rate": 4.522058823529412e-05,
|
| 98 |
+
"loss": 2.7955,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.0,
|
| 103 |
+
"eval_gen_len": 18.985347985347985,
|
| 104 |
+
"eval_loss": 2.1561412811279297,
|
| 105 |
+
"eval_rouge1": 28.5159,
|
| 106 |
+
"eval_rouge2": 14.3492,
|
| 107 |
+
"eval_rougeL": 26.0596,
|
| 108 |
+
"eval_rougeLsum": 27.2431,
|
| 109 |
+
"eval_runtime": 23.1378,
|
| 110 |
+
"eval_samples_per_second": 35.397,
|
| 111 |
+
"eval_steps_per_second": 2.247,
|
| 112 |
+
"step": 340
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.06,
|
| 116 |
+
"learning_rate": 4.485294117647059e-05,
|
| 117 |
+
"loss": 2.7598,
|
| 118 |
+
"step": 350
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.21,
|
| 122 |
+
"learning_rate": 4.448529411764706e-05,
|
| 123 |
+
"loss": 2.7091,
|
| 124 |
+
"step": 375
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.35,
|
| 128 |
+
"learning_rate": 4.411764705882353e-05,
|
| 129 |
+
"loss": 2.7055,
|
| 130 |
+
"step": 400
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.5,
|
| 134 |
+
"learning_rate": 4.375e-05,
|
| 135 |
+
"loss": 2.7163,
|
| 136 |
+
"step": 425
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.65,
|
| 140 |
+
"learning_rate": 4.3382352941176474e-05,
|
| 141 |
+
"loss": 2.6844,
|
| 142 |
+
"step": 450
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.79,
|
| 146 |
+
"learning_rate": 4.301470588235295e-05,
|
| 147 |
+
"loss": 2.686,
|
| 148 |
+
"step": 475
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.94,
|
| 152 |
+
"learning_rate": 4.2647058823529415e-05,
|
| 153 |
+
"loss": 2.6378,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.0,
|
| 158 |
+
"eval_gen_len": 18.99145299145299,
|
| 159 |
+
"eval_loss": 2.130974531173706,
|
| 160 |
+
"eval_rouge1": 28.9554,
|
| 161 |
+
"eval_rouge2": 14.6901,
|
| 162 |
+
"eval_rougeL": 26.4208,
|
| 163 |
+
"eval_rougeLsum": 27.5523,
|
| 164 |
+
"eval_runtime": 23.1305,
|
| 165 |
+
"eval_samples_per_second": 35.408,
|
| 166 |
+
"eval_steps_per_second": 2.248,
|
| 167 |
+
"step": 510
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.09,
|
| 171 |
+
"learning_rate": 4.227941176470588e-05,
|
| 172 |
+
"loss": 2.6666,
|
| 173 |
+
"step": 525
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.24,
|
| 177 |
+
"learning_rate": 4.1911764705882356e-05,
|
| 178 |
+
"loss": 2.6372,
|
| 179 |
+
"step": 550
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.38,
|
| 183 |
+
"learning_rate": 4.154411764705883e-05,
|
| 184 |
+
"loss": 2.6506,
|
| 185 |
+
"step": 575
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.53,
|
| 189 |
+
"learning_rate": 4.11764705882353e-05,
|
| 190 |
+
"loss": 2.6104,
|
| 191 |
+
"step": 600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.68,
|
| 195 |
+
"learning_rate": 4.0808823529411765e-05,
|
| 196 |
+
"loss": 2.5946,
|
| 197 |
+
"step": 625
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.82,
|
| 201 |
+
"learning_rate": 4.044117647058824e-05,
|
| 202 |
+
"loss": 2.6182,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.97,
|
| 207 |
+
"learning_rate": 4.007352941176471e-05,
|
| 208 |
+
"loss": 2.5962,
|
| 209 |
+
"step": 675
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.0,
|
| 213 |
+
"eval_gen_len": 18.99145299145299,
|
| 214 |
+
"eval_loss": 2.1109659671783447,
|
| 215 |
+
"eval_rouge1": 29.381,
|
| 216 |
+
"eval_rouge2": 15.1503,
|
| 217 |
+
"eval_rougeL": 26.8406,
|
| 218 |
+
"eval_rougeLsum": 27.9653,
|
| 219 |
+
"eval_runtime": 23.0996,
|
| 220 |
+
"eval_samples_per_second": 35.455,
|
| 221 |
+
"eval_steps_per_second": 2.251,
|
| 222 |
+
"step": 680
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.12,
|
| 226 |
+
"learning_rate": 3.970588235294117e-05,
|
| 227 |
+
"loss": 2.5478,
|
| 228 |
+
"step": 700
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.26,
|
| 232 |
+
"learning_rate": 3.933823529411765e-05,
|
| 233 |
+
"loss": 2.5601,
|
| 234 |
+
"step": 725
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.41,
|
| 238 |
+
"learning_rate": 3.897058823529412e-05,
|
| 239 |
+
"loss": 2.5793,
|
| 240 |
+
"step": 750
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 4.56,
|
| 244 |
+
"learning_rate": 3.8602941176470595e-05,
|
| 245 |
+
"loss": 2.5655,
|
| 246 |
+
"step": 775
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.71,
|
| 250 |
+
"learning_rate": 3.8235294117647055e-05,
|
| 251 |
+
"loss": 2.5686,
|
| 252 |
+
"step": 800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.85,
|
| 256 |
+
"learning_rate": 3.786764705882353e-05,
|
| 257 |
+
"loss": 2.5704,
|
| 258 |
+
"step": 825
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.0,
|
| 262 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 263 |
+
"loss": 2.5369,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.0,
|
| 268 |
+
"eval_gen_len": 18.996336996336996,
|
| 269 |
+
"eval_loss": 2.1019859313964844,
|
| 270 |
+
"eval_rouge1": 29.5767,
|
| 271 |
+
"eval_rouge2": 15.2692,
|
| 272 |
+
"eval_rougeL": 27.0113,
|
| 273 |
+
"eval_rougeLsum": 28.1849,
|
| 274 |
+
"eval_runtime": 22.9206,
|
| 275 |
+
"eval_samples_per_second": 35.732,
|
| 276 |
+
"eval_steps_per_second": 2.269,
|
| 277 |
+
"step": 850
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 5.15,
|
| 281 |
+
"learning_rate": 3.713235294117647e-05,
|
| 282 |
+
"loss": 2.5257,
|
| 283 |
+
"step": 875
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.29,
|
| 287 |
+
"learning_rate": 3.6764705882352945e-05,
|
| 288 |
+
"loss": 2.5294,
|
| 289 |
+
"step": 900
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.44,
|
| 293 |
+
"learning_rate": 3.639705882352941e-05,
|
| 294 |
+
"loss": 2.5188,
|
| 295 |
+
"step": 925
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.59,
|
| 299 |
+
"learning_rate": 3.6029411764705886e-05,
|
| 300 |
+
"loss": 2.5164,
|
| 301 |
+
"step": 950
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.74,
|
| 305 |
+
"learning_rate": 3.566176470588235e-05,
|
| 306 |
+
"loss": 2.4973,
|
| 307 |
+
"step": 975
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.88,
|
| 311 |
+
"learning_rate": 3.529411764705883e-05,
|
| 312 |
+
"loss": 2.5103,
|
| 313 |
+
"step": 1000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 6.0,
|
| 317 |
+
"eval_gen_len": 18.996336996336996,
|
| 318 |
+
"eval_loss": 2.090707302093506,
|
| 319 |
+
"eval_rouge1": 29.6354,
|
| 320 |
+
"eval_rouge2": 15.434,
|
| 321 |
+
"eval_rougeL": 27.0893,
|
| 322 |
+
"eval_rougeLsum": 28.2703,
|
| 323 |
+
"eval_runtime": 22.9931,
|
| 324 |
+
"eval_samples_per_second": 35.619,
|
| 325 |
+
"eval_steps_per_second": 2.262,
|
| 326 |
+
"step": 1020
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.03,
|
| 330 |
+
"learning_rate": 3.4926470588235294e-05,
|
| 331 |
+
"loss": 2.4817,
|
| 332 |
+
"step": 1025
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.18,
|
| 336 |
+
"learning_rate": 3.455882352941177e-05,
|
| 337 |
+
"loss": 2.4662,
|
| 338 |
+
"step": 1050
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.32,
|
| 342 |
+
"learning_rate": 3.4191176470588236e-05,
|
| 343 |
+
"loss": 2.4879,
|
| 344 |
+
"step": 1075
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.47,
|
| 348 |
+
"learning_rate": 3.382352941176471e-05,
|
| 349 |
+
"loss": 2.4666,
|
| 350 |
+
"step": 1100
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.62,
|
| 354 |
+
"learning_rate": 3.345588235294118e-05,
|
| 355 |
+
"loss": 2.4908,
|
| 356 |
+
"step": 1125
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.76,
|
| 360 |
+
"learning_rate": 3.308823529411765e-05,
|
| 361 |
+
"loss": 2.4887,
|
| 362 |
+
"step": 1150
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.91,
|
| 366 |
+
"learning_rate": 3.272058823529412e-05,
|
| 367 |
+
"loss": 2.4524,
|
| 368 |
+
"step": 1175
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 7.0,
|
| 372 |
+
"eval_gen_len": 18.996336996336996,
|
| 373 |
+
"eval_loss": 2.0839579105377197,
|
| 374 |
+
"eval_rouge1": 29.7812,
|
| 375 |
+
"eval_rouge2": 15.4963,
|
| 376 |
+
"eval_rougeL": 27.2779,
|
| 377 |
+
"eval_rougeLsum": 28.385,
|
| 378 |
+
"eval_runtime": 23.0064,
|
| 379 |
+
"eval_samples_per_second": 35.599,
|
| 380 |
+
"eval_steps_per_second": 2.26,
|
| 381 |
+
"step": 1190
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.06,
|
| 385 |
+
"learning_rate": 3.235294117647059e-05,
|
| 386 |
+
"loss": 2.4526,
|
| 387 |
+
"step": 1200
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.21,
|
| 391 |
+
"learning_rate": 3.198529411764706e-05,
|
| 392 |
+
"loss": 2.4316,
|
| 393 |
+
"step": 1225
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 7.35,
|
| 397 |
+
"learning_rate": 3.161764705882353e-05,
|
| 398 |
+
"loss": 2.4511,
|
| 399 |
+
"step": 1250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 7.5,
|
| 403 |
+
"learning_rate": 3.125e-05,
|
| 404 |
+
"loss": 2.4642,
|
| 405 |
+
"step": 1275
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 7.65,
|
| 409 |
+
"learning_rate": 3.0882352941176475e-05,
|
| 410 |
+
"loss": 2.4387,
|
| 411 |
+
"step": 1300
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 7.79,
|
| 415 |
+
"learning_rate": 3.0514705882352945e-05,
|
| 416 |
+
"loss": 2.477,
|
| 417 |
+
"step": 1325
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 7.94,
|
| 421 |
+
"learning_rate": 3.0147058823529413e-05,
|
| 422 |
+
"loss": 2.4472,
|
| 423 |
+
"step": 1350
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.0,
|
| 427 |
+
"eval_gen_len": 18.996336996336996,
|
| 428 |
+
"eval_loss": 2.0799622535705566,
|
| 429 |
+
"eval_rouge1": 29.6011,
|
| 430 |
+
"eval_rouge2": 15.5138,
|
| 431 |
+
"eval_rougeL": 27.1381,
|
| 432 |
+
"eval_rougeLsum": 28.2799,
|
| 433 |
+
"eval_runtime": 22.9827,
|
| 434 |
+
"eval_samples_per_second": 35.636,
|
| 435 |
+
"eval_steps_per_second": 2.263,
|
| 436 |
+
"step": 1360
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 8.09,
|
| 440 |
+
"learning_rate": 2.9779411764705883e-05,
|
| 441 |
+
"loss": 2.4296,
|
| 442 |
+
"step": 1375
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 8.24,
|
| 446 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 447 |
+
"loss": 2.4109,
|
| 448 |
+
"step": 1400
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 8.38,
|
| 452 |
+
"learning_rate": 2.9044117647058828e-05,
|
| 453 |
+
"loss": 2.4181,
|
| 454 |
+
"step": 1425
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 8.53,
|
| 458 |
+
"learning_rate": 2.8676470588235295e-05,
|
| 459 |
+
"loss": 2.4089,
|
| 460 |
+
"step": 1450
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 8.68,
|
| 464 |
+
"learning_rate": 2.8308823529411766e-05,
|
| 465 |
+
"loss": 2.4518,
|
| 466 |
+
"step": 1475
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 8.82,
|
| 470 |
+
"learning_rate": 2.7941176470588236e-05,
|
| 471 |
+
"loss": 2.4271,
|
| 472 |
+
"step": 1500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 8.97,
|
| 476 |
+
"learning_rate": 2.757352941176471e-05,
|
| 477 |
+
"loss": 2.4089,
|
| 478 |
+
"step": 1525
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 9.0,
|
| 482 |
+
"eval_gen_len": 18.996336996336996,
|
| 483 |
+
"eval_loss": 2.075223207473755,
|
| 484 |
+
"eval_rouge1": 29.7647,
|
| 485 |
+
"eval_rouge2": 15.6183,
|
| 486 |
+
"eval_rougeL": 27.318,
|
| 487 |
+
"eval_rougeLsum": 28.4747,
|
| 488 |
+
"eval_runtime": 22.8902,
|
| 489 |
+
"eval_samples_per_second": 35.779,
|
| 490 |
+
"eval_steps_per_second": 2.272,
|
| 491 |
+
"step": 1530
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.12,
|
| 495 |
+
"learning_rate": 2.7205882352941174e-05,
|
| 496 |
+
"loss": 2.4048,
|
| 497 |
+
"step": 1550
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 9.26,
|
| 501 |
+
"learning_rate": 2.6838235294117648e-05,
|
| 502 |
+
"loss": 2.4132,
|
| 503 |
+
"step": 1575
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.41,
|
| 507 |
+
"learning_rate": 2.647058823529412e-05,
|
| 508 |
+
"loss": 2.3885,
|
| 509 |
+
"step": 1600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 9.56,
|
| 513 |
+
"learning_rate": 2.6102941176470593e-05,
|
| 514 |
+
"loss": 2.4007,
|
| 515 |
+
"step": 1625
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.71,
|
| 519 |
+
"learning_rate": 2.5735294117647057e-05,
|
| 520 |
+
"loss": 2.4089,
|
| 521 |
+
"step": 1650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 9.85,
|
| 525 |
+
"learning_rate": 2.536764705882353e-05,
|
| 526 |
+
"loss": 2.3912,
|
| 527 |
+
"step": 1675
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 10.0,
|
| 531 |
+
"learning_rate": 2.5e-05,
|
| 532 |
+
"loss": 2.4011,
|
| 533 |
+
"step": 1700
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 10.0,
|
| 537 |
+
"eval_gen_len": 19.0,
|
| 538 |
+
"eval_loss": 2.071033239364624,
|
| 539 |
+
"eval_rouge1": 29.6533,
|
| 540 |
+
"eval_rouge2": 15.5536,
|
| 541 |
+
"eval_rougeL": 27.2687,
|
| 542 |
+
"eval_rougeLsum": 28.4457,
|
| 543 |
+
"eval_runtime": 23.0214,
|
| 544 |
+
"eval_samples_per_second": 35.576,
|
| 545 |
+
"eval_steps_per_second": 2.259,
|
| 546 |
+
"step": 1700
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 10.15,
|
| 550 |
+
"learning_rate": 2.4632352941176472e-05,
|
| 551 |
+
"loss": 2.4049,
|
| 552 |
+
"step": 1725
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 10.29,
|
| 556 |
+
"learning_rate": 2.4264705882352942e-05,
|
| 557 |
+
"loss": 2.3802,
|
| 558 |
+
"step": 1750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 10.44,
|
| 562 |
+
"learning_rate": 2.3897058823529413e-05,
|
| 563 |
+
"loss": 2.3688,
|
| 564 |
+
"step": 1775
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 10.59,
|
| 568 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 569 |
+
"loss": 2.3897,
|
| 570 |
+
"step": 1800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 10.74,
|
| 574 |
+
"learning_rate": 2.3161764705882354e-05,
|
| 575 |
+
"loss": 2.3464,
|
| 576 |
+
"step": 1825
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 10.88,
|
| 580 |
+
"learning_rate": 2.2794117647058825e-05,
|
| 581 |
+
"loss": 2.3792,
|
| 582 |
+
"step": 1850
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 11.0,
|
| 586 |
+
"eval_gen_len": 19.0,
|
| 587 |
+
"eval_loss": 2.0655674934387207,
|
| 588 |
+
"eval_rouge1": 29.8668,
|
| 589 |
+
"eval_rouge2": 15.6931,
|
| 590 |
+
"eval_rougeL": 27.4208,
|
| 591 |
+
"eval_rougeLsum": 28.5477,
|
| 592 |
+
"eval_runtime": 21.951,
|
| 593 |
+
"eval_samples_per_second": 37.31,
|
| 594 |
+
"eval_steps_per_second": 2.369,
|
| 595 |
+
"step": 1870
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 11.03,
|
| 599 |
+
"learning_rate": 2.2426470588235296e-05,
|
| 600 |
+
"loss": 2.3783,
|
| 601 |
+
"step": 1875
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 11.18,
|
| 605 |
+
"learning_rate": 2.2058823529411766e-05,
|
| 606 |
+
"loss": 2.3446,
|
| 607 |
+
"step": 1900
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 11.32,
|
| 611 |
+
"learning_rate": 2.1691176470588237e-05,
|
| 612 |
+
"loss": 2.3929,
|
| 613 |
+
"step": 1925
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 11.47,
|
| 617 |
+
"learning_rate": 2.1323529411764707e-05,
|
| 618 |
+
"loss": 2.374,
|
| 619 |
+
"step": 1950
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 11.62,
|
| 623 |
+
"learning_rate": 2.0955882352941178e-05,
|
| 624 |
+
"loss": 2.3544,
|
| 625 |
+
"step": 1975
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 11.76,
|
| 629 |
+
"learning_rate": 2.058823529411765e-05,
|
| 630 |
+
"loss": 2.357,
|
| 631 |
+
"step": 2000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 11.91,
|
| 635 |
+
"learning_rate": 2.022058823529412e-05,
|
| 636 |
+
"loss": 2.3588,
|
| 637 |
+
"step": 2025
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 12.0,
|
| 641 |
+
"eval_gen_len": 18.996336996336996,
|
| 642 |
+
"eval_loss": 2.0634803771972656,
|
| 643 |
+
"eval_rouge1": 29.8378,
|
| 644 |
+
"eval_rouge2": 15.682,
|
| 645 |
+
"eval_rougeL": 27.4635,
|
| 646 |
+
"eval_rougeLsum": 28.5803,
|
| 647 |
+
"eval_runtime": 22.98,
|
| 648 |
+
"eval_samples_per_second": 35.64,
|
| 649 |
+
"eval_steps_per_second": 2.263,
|
| 650 |
+
"step": 2040
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 12.06,
|
| 654 |
+
"learning_rate": 1.9852941176470586e-05,
|
| 655 |
+
"loss": 2.3503,
|
| 656 |
+
"step": 2050
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 12.21,
|
| 660 |
+
"learning_rate": 1.948529411764706e-05,
|
| 661 |
+
"loss": 2.3402,
|
| 662 |
+
"step": 2075
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 12.35,
|
| 666 |
+
"learning_rate": 1.9117647058823528e-05,
|
| 667 |
+
"loss": 2.3716,
|
| 668 |
+
"step": 2100
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 12.5,
|
| 672 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 673 |
+
"loss": 2.3161,
|
| 674 |
+
"step": 2125
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 12.65,
|
| 678 |
+
"learning_rate": 1.8382352941176472e-05,
|
| 679 |
+
"loss": 2.3354,
|
| 680 |
+
"step": 2150
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 12.79,
|
| 684 |
+
"learning_rate": 1.8014705882352943e-05,
|
| 685 |
+
"loss": 2.3476,
|
| 686 |
+
"step": 2175
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 12.94,
|
| 690 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 691 |
+
"loss": 2.3397,
|
| 692 |
+
"step": 2200
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 13.0,
|
| 696 |
+
"eval_gen_len": 19.0,
|
| 697 |
+
"eval_loss": 2.0630440711975098,
|
| 698 |
+
"eval_rouge1": 29.9043,
|
| 699 |
+
"eval_rouge2": 15.7535,
|
| 700 |
+
"eval_rougeL": 27.5065,
|
| 701 |
+
"eval_rougeLsum": 28.6539,
|
| 702 |
+
"eval_runtime": 22.9094,
|
| 703 |
+
"eval_samples_per_second": 35.75,
|
| 704 |
+
"eval_steps_per_second": 2.27,
|
| 705 |
+
"step": 2210
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 13.09,
|
| 709 |
+
"learning_rate": 1.7279411764705884e-05,
|
| 710 |
+
"loss": 2.3399,
|
| 711 |
+
"step": 2225
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 13.24,
|
| 715 |
+
"learning_rate": 1.6911764705882355e-05,
|
| 716 |
+
"loss": 2.3207,
|
| 717 |
+
"step": 2250
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 13.38,
|
| 721 |
+
"learning_rate": 1.6544117647058825e-05,
|
| 722 |
+
"loss": 2.3339,
|
| 723 |
+
"step": 2275
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 13.53,
|
| 727 |
+
"learning_rate": 1.6176470588235296e-05,
|
| 728 |
+
"loss": 2.3347,
|
| 729 |
+
"step": 2300
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 13.68,
|
| 733 |
+
"learning_rate": 1.5808823529411763e-05,
|
| 734 |
+
"loss": 2.3318,
|
| 735 |
+
"step": 2325
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 13.82,
|
| 739 |
+
"learning_rate": 1.5441176470588237e-05,
|
| 740 |
+
"loss": 2.3275,
|
| 741 |
+
"step": 2350
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 13.97,
|
| 745 |
+
"learning_rate": 1.5073529411764706e-05,
|
| 746 |
+
"loss": 2.3201,
|
| 747 |
+
"step": 2375
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 14.0,
|
| 751 |
+
"eval_gen_len": 18.996336996336996,
|
| 752 |
+
"eval_loss": 2.0599966049194336,
|
| 753 |
+
"eval_rouge1": 29.7926,
|
| 754 |
+
"eval_rouge2": 15.7077,
|
| 755 |
+
"eval_rougeL": 27.4066,
|
| 756 |
+
"eval_rougeLsum": 28.5302,
|
| 757 |
+
"eval_runtime": 23.1182,
|
| 758 |
+
"eval_samples_per_second": 35.427,
|
| 759 |
+
"eval_steps_per_second": 2.249,
|
| 760 |
+
"step": 2380
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 14.12,
|
| 764 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 765 |
+
"loss": 2.3204,
|
| 766 |
+
"step": 2400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 14.26,
|
| 770 |
+
"learning_rate": 1.4338235294117647e-05,
|
| 771 |
+
"loss": 2.3592,
|
| 772 |
+
"step": 2425
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 14.41,
|
| 776 |
+
"learning_rate": 1.3970588235294118e-05,
|
| 777 |
+
"loss": 2.3275,
|
| 778 |
+
"step": 2450
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 14.56,
|
| 782 |
+
"learning_rate": 1.3602941176470587e-05,
|
| 783 |
+
"loss": 2.2936,
|
| 784 |
+
"step": 2475
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 14.71,
|
| 788 |
+
"learning_rate": 1.323529411764706e-05,
|
| 789 |
+
"loss": 2.3013,
|
| 790 |
+
"step": 2500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 14.85,
|
| 794 |
+
"learning_rate": 1.2867647058823528e-05,
|
| 795 |
+
"loss": 2.3007,
|
| 796 |
+
"step": 2525
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 15.0,
|
| 800 |
+
"learning_rate": 1.25e-05,
|
| 801 |
+
"loss": 2.3241,
|
| 802 |
+
"step": 2550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 15.0,
|
| 806 |
+
"eval_gen_len": 19.0,
|
| 807 |
+
"eval_loss": 2.0615200996398926,
|
| 808 |
+
"eval_rouge1": 29.8536,
|
| 809 |
+
"eval_rouge2": 15.7929,
|
| 810 |
+
"eval_rougeL": 27.4572,
|
| 811 |
+
"eval_rougeLsum": 28.5704,
|
| 812 |
+
"eval_runtime": 22.9087,
|
| 813 |
+
"eval_samples_per_second": 35.751,
|
| 814 |
+
"eval_steps_per_second": 2.27,
|
| 815 |
+
"step": 2550
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 15.15,
|
| 819 |
+
"learning_rate": 1.2132352941176471e-05,
|
| 820 |
+
"loss": 2.326,
|
| 821 |
+
"step": 2575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 15.29,
|
| 825 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 826 |
+
"loss": 2.3004,
|
| 827 |
+
"step": 2600
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 15.44,
|
| 831 |
+
"learning_rate": 1.1397058823529412e-05,
|
| 832 |
+
"loss": 2.311,
|
| 833 |
+
"step": 2625
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 15.59,
|
| 837 |
+
"learning_rate": 1.1029411764705883e-05,
|
| 838 |
+
"loss": 2.3427,
|
| 839 |
+
"step": 2650
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 15.74,
|
| 843 |
+
"learning_rate": 1.0661764705882354e-05,
|
| 844 |
+
"loss": 2.2741,
|
| 845 |
+
"step": 2675
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 15.88,
|
| 849 |
+
"learning_rate": 1.0294117647058824e-05,
|
| 850 |
+
"loss": 2.3183,
|
| 851 |
+
"step": 2700
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 16.0,
|
| 855 |
+
"eval_gen_len": 19.0,
|
| 856 |
+
"eval_loss": 2.0573582649230957,
|
| 857 |
+
"eval_rouge1": 29.7529,
|
| 858 |
+
"eval_rouge2": 15.6729,
|
| 859 |
+
"eval_rougeL": 27.3388,
|
| 860 |
+
"eval_rougeLsum": 28.4678,
|
| 861 |
+
"eval_runtime": 23.1299,
|
| 862 |
+
"eval_samples_per_second": 35.409,
|
| 863 |
+
"eval_steps_per_second": 2.248,
|
| 864 |
+
"step": 2720
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 16.03,
|
| 868 |
+
"learning_rate": 9.926470588235293e-06,
|
| 869 |
+
"loss": 2.2934,
|
| 870 |
+
"step": 2725
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 16.18,
|
| 874 |
+
"learning_rate": 9.558823529411764e-06,
|
| 875 |
+
"loss": 2.2633,
|
| 876 |
+
"step": 2750
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 16.32,
|
| 880 |
+
"learning_rate": 9.191176470588236e-06,
|
| 881 |
+
"loss": 2.2957,
|
| 882 |
+
"step": 2775
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 16.47,
|
| 886 |
+
"learning_rate": 8.823529411764707e-06,
|
| 887 |
+
"loss": 2.3083,
|
| 888 |
+
"step": 2800
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 16.62,
|
| 892 |
+
"learning_rate": 8.455882352941177e-06,
|
| 893 |
+
"loss": 2.3246,
|
| 894 |
+
"step": 2825
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 16.76,
|
| 898 |
+
"learning_rate": 8.088235294117648e-06,
|
| 899 |
+
"loss": 2.2989,
|
| 900 |
+
"step": 2850
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 16.91,
|
| 904 |
+
"learning_rate": 7.720588235294119e-06,
|
| 905 |
+
"loss": 2.3346,
|
| 906 |
+
"step": 2875
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 17.0,
|
| 910 |
+
"eval_gen_len": 19.0,
|
| 911 |
+
"eval_loss": 2.0570528507232666,
|
| 912 |
+
"eval_rouge1": 29.7443,
|
| 913 |
+
"eval_rouge2": 15.6459,
|
| 914 |
+
"eval_rougeL": 27.3245,
|
| 915 |
+
"eval_rougeLsum": 28.4549,
|
| 916 |
+
"eval_runtime": 22.9331,
|
| 917 |
+
"eval_samples_per_second": 35.713,
|
| 918 |
+
"eval_steps_per_second": 2.267,
|
| 919 |
+
"step": 2890
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 17.06,
|
| 923 |
+
"learning_rate": 7.3529411764705884e-06,
|
| 924 |
+
"loss": 2.2887,
|
| 925 |
+
"step": 2900
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 17.21,
|
| 929 |
+
"learning_rate": 6.985294117647059e-06,
|
| 930 |
+
"loss": 2.2881,
|
| 931 |
+
"step": 2925
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 17.35,
|
| 935 |
+
"learning_rate": 6.61764705882353e-06,
|
| 936 |
+
"loss": 2.3062,
|
| 937 |
+
"step": 2950
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 17.5,
|
| 941 |
+
"learning_rate": 6.25e-06,
|
| 942 |
+
"loss": 2.2867,
|
| 943 |
+
"step": 2975
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 17.65,
|
| 947 |
+
"learning_rate": 5.882352941176471e-06,
|
| 948 |
+
"loss": 2.3056,
|
| 949 |
+
"step": 3000
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 17.79,
|
| 953 |
+
"learning_rate": 5.5147058823529415e-06,
|
| 954 |
+
"loss": 2.3098,
|
| 955 |
+
"step": 3025
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 17.94,
|
| 959 |
+
"learning_rate": 5.147058823529412e-06,
|
| 960 |
+
"loss": 2.2932,
|
| 961 |
+
"step": 3050
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 18.0,
|
| 965 |
+
"eval_gen_len": 19.0,
|
| 966 |
+
"eval_loss": 2.0577263832092285,
|
| 967 |
+
"eval_rouge1": 29.7467,
|
| 968 |
+
"eval_rouge2": 15.6717,
|
| 969 |
+
"eval_rougeL": 27.3391,
|
| 970 |
+
"eval_rougeLsum": 28.4541,
|
| 971 |
+
"eval_runtime": 23.0624,
|
| 972 |
+
"eval_samples_per_second": 35.512,
|
| 973 |
+
"eval_steps_per_second": 2.255,
|
| 974 |
+
"step": 3060
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 18.09,
|
| 978 |
+
"learning_rate": 4.779411764705882e-06,
|
| 979 |
+
"loss": 2.2832,
|
| 980 |
+
"step": 3075
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 18.24,
|
| 984 |
+
"learning_rate": 4.411764705882353e-06,
|
| 985 |
+
"loss": 2.289,
|
| 986 |
+
"step": 3100
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 18.38,
|
| 990 |
+
"learning_rate": 4.044117647058824e-06,
|
| 991 |
+
"loss": 2.2932,
|
| 992 |
+
"step": 3125
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 18.53,
|
| 996 |
+
"learning_rate": 3.6764705882352942e-06,
|
| 997 |
+
"loss": 2.3085,
|
| 998 |
+
"step": 3150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 18.68,
|
| 1002 |
+
"learning_rate": 3.308823529411765e-06,
|
| 1003 |
+
"loss": 2.2884,
|
| 1004 |
+
"step": 3175
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 18.82,
|
| 1008 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 1009 |
+
"loss": 2.2877,
|
| 1010 |
+
"step": 3200
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 18.97,
|
| 1014 |
+
"learning_rate": 2.573529411764706e-06,
|
| 1015 |
+
"loss": 2.2755,
|
| 1016 |
+
"step": 3225
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 19.0,
|
| 1020 |
+
"eval_gen_len": 19.0,
|
| 1021 |
+
"eval_loss": 2.0573978424072266,
|
| 1022 |
+
"eval_rouge1": 29.7694,
|
| 1023 |
+
"eval_rouge2": 15.6776,
|
| 1024 |
+
"eval_rougeL": 27.3556,
|
| 1025 |
+
"eval_rougeLsum": 28.4819,
|
| 1026 |
+
"eval_runtime": 22.951,
|
| 1027 |
+
"eval_samples_per_second": 35.685,
|
| 1028 |
+
"eval_steps_per_second": 2.266,
|
| 1029 |
+
"step": 3230
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 19.0,
|
| 1033 |
+
"step": 3230,
|
| 1034 |
+
"total_flos": 2.285170027491492e+17,
|
| 1035 |
+
"train_loss": 2.4905450729393737,
|
| 1036 |
+
"train_runtime": 8327.4677,
|
| 1037 |
+
"train_samples_per_second": 26.116,
|
| 1038 |
+
"train_steps_per_second": 0.408
|
| 1039 |
+
}
|
| 1040 |
+
],
|
| 1041 |
+
"max_steps": 3400,
|
| 1042 |
+
"num_train_epochs": 20,
|
| 1043 |
+
"total_flos": 2.285170027491492e+17,
|
| 1044 |
+
"trial_name": null,
|
| 1045 |
+
"trial_params": null
|
| 1046 |
+
}
|