End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1678049310.gifu.4009013.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.6327515490927386,
|
| 4 |
+
"eval_loss": 1.86328125,
|
| 5 |
+
"eval_runtime": 1039.3969,
|
| 6 |
+
"eval_samples": 308356,
|
| 7 |
+
"eval_samples_per_second": 296.668,
|
| 8 |
+
"eval_steps_per_second": 4.636,
|
| 9 |
+
"perplexity": 6.44484927647148,
|
| 10 |
+
"train_loss": 2.572186891088575,
|
| 11 |
+
"train_runtime": 307115.8978,
|
| 12 |
+
"train_samples": 5858758,
|
| 13 |
+
"train_samples_per_second": 95.384,
|
| 14 |
+
"train_steps_per_second": 1.49
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.6327515490927386,
|
| 4 |
+
"eval_loss": 1.86328125,
|
| 5 |
+
"eval_runtime": 1039.3969,
|
| 6 |
+
"eval_samples": 308356,
|
| 7 |
+
"eval_samples_per_second": 296.668,
|
| 8 |
+
"eval_steps_per_second": 4.636,
|
| 9 |
+
"perplexity": 6.44484927647148
|
| 10 |
+
}
|
logs/events.out.tfevents.1678049310.gifu.4009013.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233dd3afff213c29231c4677495c3e4f17d895d5672edee625363da96027fc49
|
| 3 |
+
size 369
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 2.572186891088575,
|
| 4 |
+
"train_runtime": 307115.8978,
|
| 5 |
+
"train_samples": 5858758,
|
| 6 |
+
"train_samples_per_second": 95.384,
|
| 7 |
+
"train_steps_per_second": 1.49
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|