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": 27.1659,
|
| 4 |
+
"eval_gen_len": 43.9575,
|
| 5 |
+
"eval_loss": 1.3594460487365723,
|
| 6 |
+
"eval_runtime": 602.2531,
|
| 7 |
+
"eval_samples": 1999,
|
| 8 |
+
"eval_samples_per_second": 3.319,
|
| 9 |
+
"eval_steps_per_second": 0.415,
|
| 10 |
+
"train_loss": 0.6004852689742292,
|
| 11 |
+
"train_runtime": 403004.475,
|
| 12 |
+
"train_samples": 610320,
|
| 13 |
+
"train_samples_per_second": 15.144,
|
| 14 |
+
"train_steps_per_second": 3.786
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_bleu": 27.1659,
|
| 4 |
+
"eval_gen_len": 43.9575,
|
| 5 |
+
"eval_loss": 1.3594460487365723,
|
| 6 |
+
"eval_runtime": 602.2531,
|
| 7 |
+
"eval_samples": 1999,
|
| 8 |
+
"eval_samples_per_second": 3.319,
|
| 9 |
+
"eval_steps_per_second": 0.415
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.6004852689742292,
|
| 4 |
+
"train_runtime": 403004.475,
|
| 5 |
+
"train_samples": 610320,
|
| 6 |
+
"train_samples_per_second": 15.144,
|
| 7 |
+
"train_steps_per_second": 3.786
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|