End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_bleu": 23.6759,
|
| 4 |
+
"eval_gen_len": 43.6993,
|
| 5 |
+
"eval_loss": 1.6327831745147705,
|
| 6 |
+
"eval_runtime": 423.5956,
|
| 7 |
+
"eval_samples": 1999,
|
| 8 |
+
"eval_samples_per_second": 4.719,
|
| 9 |
+
"eval_steps_per_second": 0.59,
|
| 10 |
+
"train_loss": 1.0178077638950866,
|
| 11 |
+
"train_runtime": 115805.9671,
|
| 12 |
+
"train_samples": 610320,
|
| 13 |
+
"train_samples_per_second": 52.702,
|
| 14 |
+
"train_steps_per_second": 4.392
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_bleu": 23.6759,
|
| 4 |
+
"eval_gen_len": 43.6993,
|
| 5 |
+
"eval_loss": 1.6327831745147705,
|
| 6 |
+
"eval_runtime": 423.5956,
|
| 7 |
+
"eval_samples": 1999,
|
| 8 |
+
"eval_samples_per_second": 4.719,
|
| 9 |
+
"eval_steps_per_second": 0.59
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.0178077638950866,
|
| 4 |
+
"train_runtime": 115805.9671,
|
| 5 |
+
"train_samples": 610320,
|
| 6 |
+
"train_samples_per_second": 52.702,
|
| 7 |
+
"train_steps_per_second": 4.392
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|