Commit
•
ab5f589
1
Parent(s):
4ec1261
🍻 cheers
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Sep29_14-54-32_9c904309c746/events.out.tfevents.1664466585.9c904309c746.68.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +2320 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9107332624867163,
|
| 4 |
+
"eval_loss": 0.2977409064769745,
|
| 5 |
+
"eval_runtime": 33.2004,
|
| 6 |
+
"eval_samples_per_second": 28.343,
|
| 7 |
+
"eval_steps_per_second": 3.554,
|
| 8 |
+
"total_flos": 1.3394666639602483e+18,
|
| 9 |
+
"train_loss": 0.2829396238287648,
|
| 10 |
+
"train_runtime": 3129.5189,
|
| 11 |
+
"train_samples_per_second": 17.025,
|
| 12 |
+
"train_steps_per_second": 1.064
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9107332624867163,
|
| 4 |
+
"eval_loss": 0.2977409064769745,
|
| 5 |
+
"eval_runtime": 33.2004,
|
| 6 |
+
"eval_samples_per_second": 28.343,
|
| 7 |
+
"eval_steps_per_second": 3.554
|
| 8 |
+
}
|
runs/Sep29_14-54-32_9c904309c746/events.out.tfevents.1664466585.9c904309c746.68.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b15da2b261bef08dee728597b35079bf5ebb79953d27b6f783badf78c88e8674
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.3394666639602483e+18,
|
| 4 |
+
"train_loss": 0.2829396238287648,
|
| 5 |
+
"train_runtime": 3129.5189,
|
| 6 |
+
"train_samples_per_second": 17.025,
|
| 7 |
+
"train_steps_per_second": 1.064
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2320 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2977409064769745,
|
| 3 |
+
"best_model_checkpoint": "finetuned-ConvNext-Indian-food/checkpoint-1300",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 3330,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0001993993993993994,
|
| 13 |
+
"loss": 2.9337,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 0.0001987987987987988,
|
| 19 |
+
"loss": 2.7589,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 0.0001981981981981982,
|
| 25 |
+
"loss": 2.4837,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 0.0001975975975975976,
|
| 31 |
+
"loss": 2.2961,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 0.00019699699699699701,
|
| 37 |
+
"loss": 2.1006,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 0.0001963963963963964,
|
| 43 |
+
"loss": 1.8491,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 0.00019579579579579582,
|
| 49 |
+
"loss": 1.637,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 0.0001951951951951952,
|
| 55 |
+
"loss": 1.4124,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.27,
|
| 60 |
+
"learning_rate": 0.00019459459459459462,
|
| 61 |
+
"loss": 1.3069,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.3,
|
| 66 |
+
"learning_rate": 0.00019399399399399402,
|
| 67 |
+
"loss": 1.3145,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.3,
|
| 72 |
+
"eval_accuracy": 0.8150903294367694,
|
| 73 |
+
"eval_loss": 1.0460201501846313,
|
| 74 |
+
"eval_runtime": 32.8174,
|
| 75 |
+
"eval_samples_per_second": 28.674,
|
| 76 |
+
"eval_steps_per_second": 3.596,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.33,
|
| 81 |
+
"learning_rate": 0.0001933933933933934,
|
| 82 |
+
"loss": 1.2783,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.36,
|
| 87 |
+
"learning_rate": 0.00019279279279279282,
|
| 88 |
+
"loss": 1.0547,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.39,
|
| 93 |
+
"learning_rate": 0.00019225225225225225,
|
| 94 |
+
"loss": 1.0143,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.42,
|
| 99 |
+
"learning_rate": 0.00019165165165165165,
|
| 100 |
+
"loss": 0.9249,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.45,
|
| 105 |
+
"learning_rate": 0.00019105105105105105,
|
| 106 |
+
"loss": 0.8564,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.48,
|
| 111 |
+
"learning_rate": 0.00019045045045045048,
|
| 112 |
+
"loss": 0.8674,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.51,
|
| 117 |
+
"learning_rate": 0.00018984984984984985,
|
| 118 |
+
"loss": 0.9013,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.54,
|
| 123 |
+
"learning_rate": 0.00018924924924924925,
|
| 124 |
+
"loss": 0.7794,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.57,
|
| 129 |
+
"learning_rate": 0.00018864864864864866,
|
| 130 |
+
"loss": 0.7487,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.6,
|
| 135 |
+
"learning_rate": 0.00018804804804804806,
|
| 136 |
+
"loss": 0.6694,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.6,
|
| 141 |
+
"eval_accuracy": 0.8756641870350691,
|
| 142 |
+
"eval_loss": 0.5439420938491821,
|
| 143 |
+
"eval_runtime": 32.7659,
|
| 144 |
+
"eval_samples_per_second": 28.719,
|
| 145 |
+
"eval_steps_per_second": 3.601,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.63,
|
| 150 |
+
"learning_rate": 0.00018744744744744746,
|
| 151 |
+
"loss": 0.7296,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.66,
|
| 156 |
+
"learning_rate": 0.00018684684684684686,
|
| 157 |
+
"loss": 0.6253,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"learning_rate": 0.00018624624624624626,
|
| 163 |
+
"loss": 0.5394,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.72,
|
| 168 |
+
"learning_rate": 0.00018564564564564566,
|
| 169 |
+
"loss": 0.6077,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.75,
|
| 174 |
+
"learning_rate": 0.00018504504504504506,
|
| 175 |
+
"loss": 0.6871,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.78,
|
| 180 |
+
"learning_rate": 0.00018444444444444446,
|
| 181 |
+
"loss": 0.6409,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.81,
|
| 186 |
+
"learning_rate": 0.00018384384384384386,
|
| 187 |
+
"loss": 0.6477,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.84,
|
| 192 |
+
"learning_rate": 0.00018324324324324324,
|
| 193 |
+
"loss": 0.7863,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.87,
|
| 198 |
+
"learning_rate": 0.00018264264264264266,
|
| 199 |
+
"loss": 0.563,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.9,
|
| 204 |
+
"learning_rate": 0.00018204204204204204,
|
| 205 |
+
"loss": 0.5057,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9,
|
| 210 |
+
"eval_accuracy": 0.8831030818278427,
|
| 211 |
+
"eval_loss": 0.439805269241333,
|
| 212 |
+
"eval_runtime": 33.0097,
|
| 213 |
+
"eval_samples_per_second": 28.507,
|
| 214 |
+
"eval_steps_per_second": 3.575,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.93,
|
| 219 |
+
"learning_rate": 0.00018144144144144144,
|
| 220 |
+
"loss": 0.4947,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.96,
|
| 225 |
+
"learning_rate": 0.00018084084084084084,
|
| 226 |
+
"loss": 0.5115,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.99,
|
| 231 |
+
"learning_rate": 0.00018024024024024024,
|
| 232 |
+
"loss": 0.4236,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.02,
|
| 237 |
+
"learning_rate": 0.00017963963963963967,
|
| 238 |
+
"loss": 0.4525,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.05,
|
| 243 |
+
"learning_rate": 0.00017903903903903904,
|
| 244 |
+
"loss": 0.5395,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.08,
|
| 249 |
+
"learning_rate": 0.00017843843843843844,
|
| 250 |
+
"loss": 0.3434,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.11,
|
| 255 |
+
"learning_rate": 0.00017783783783783784,
|
| 256 |
+
"loss": 0.2957,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.14,
|
| 261 |
+
"learning_rate": 0.00017723723723723724,
|
| 262 |
+
"loss": 0.3677,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.17,
|
| 267 |
+
"learning_rate": 0.00017663663663663665,
|
| 268 |
+
"loss": 0.4456,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.2,
|
| 273 |
+
"learning_rate": 0.0001760960960960961,
|
| 274 |
+
"loss": 0.4381,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.2,
|
| 279 |
+
"eval_accuracy": 0.8820403825717322,
|
| 280 |
+
"eval_loss": 0.42858749628067017,
|
| 281 |
+
"eval_runtime": 32.2263,
|
| 282 |
+
"eval_samples_per_second": 29.2,
|
| 283 |
+
"eval_steps_per_second": 3.662,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.23,
|
| 288 |
+
"learning_rate": 0.0001754954954954955,
|
| 289 |
+
"loss": 0.5108,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.26,
|
| 294 |
+
"learning_rate": 0.0001748948948948949,
|
| 295 |
+
"loss": 0.501,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.29,
|
| 300 |
+
"learning_rate": 0.0001742942942942943,
|
| 301 |
+
"loss": 0.319,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.32,
|
| 306 |
+
"learning_rate": 0.0001736936936936937,
|
| 307 |
+
"loss": 0.3744,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.35,
|
| 312 |
+
"learning_rate": 0.0001730930930930931,
|
| 313 |
+
"loss": 0.4664,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.38,
|
| 318 |
+
"learning_rate": 0.0001724924924924925,
|
| 319 |
+
"loss": 0.5735,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.41,
|
| 324 |
+
"learning_rate": 0.0001718918918918919,
|
| 325 |
+
"loss": 0.2927,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.44,
|
| 330 |
+
"learning_rate": 0.00017129129129129128,
|
| 331 |
+
"loss": 0.5256,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.47,
|
| 336 |
+
"learning_rate": 0.0001706906906906907,
|
| 337 |
+
"loss": 0.4009,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.5,
|
| 342 |
+
"learning_rate": 0.00017009009009009008,
|
| 343 |
+
"loss": 0.4376,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.5,
|
| 348 |
+
"eval_accuracy": 0.9043570669500531,
|
| 349 |
+
"eval_loss": 0.34000876545906067,
|
| 350 |
+
"eval_runtime": 32.3032,
|
| 351 |
+
"eval_samples_per_second": 29.13,
|
| 352 |
+
"eval_steps_per_second": 3.653,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.53,
|
| 357 |
+
"learning_rate": 0.0001694894894894895,
|
| 358 |
+
"loss": 0.4056,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.56,
|
| 363 |
+
"learning_rate": 0.00016888888888888889,
|
| 364 |
+
"loss": 0.4832,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.59,
|
| 369 |
+
"learning_rate": 0.0001682882882882883,
|
| 370 |
+
"loss": 0.488,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.62,
|
| 375 |
+
"learning_rate": 0.0001676876876876877,
|
| 376 |
+
"loss": 0.3927,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.65,
|
| 381 |
+
"learning_rate": 0.0001670870870870871,
|
| 382 |
+
"loss": 0.3167,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.68,
|
| 387 |
+
"learning_rate": 0.00016648648648648652,
|
| 388 |
+
"loss": 0.3411,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.71,
|
| 393 |
+
"learning_rate": 0.0001658858858858859,
|
| 394 |
+
"loss": 0.3771,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.74,
|
| 399 |
+
"learning_rate": 0.0001652852852852853,
|
| 400 |
+
"loss": 0.3965,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.77,
|
| 405 |
+
"learning_rate": 0.0001646846846846847,
|
| 406 |
+
"loss": 0.5483,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.8,
|
| 411 |
+
"learning_rate": 0.0001640840840840841,
|
| 412 |
+
"loss": 0.2499,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.8,
|
| 417 |
+
"eval_accuracy": 0.9064824654622742,
|
| 418 |
+
"eval_loss": 0.3312312662601471,
|
| 419 |
+
"eval_runtime": 32.7174,
|
| 420 |
+
"eval_samples_per_second": 28.761,
|
| 421 |
+
"eval_steps_per_second": 3.607,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.83,
|
| 426 |
+
"learning_rate": 0.0001634834834834835,
|
| 427 |
+
"loss": 0.3226,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.86,
|
| 432 |
+
"learning_rate": 0.0001628828828828829,
|
| 433 |
+
"loss": 0.2392,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.89,
|
| 438 |
+
"learning_rate": 0.0001622822822822823,
|
| 439 |
+
"loss": 0.5277,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.92,
|
| 444 |
+
"learning_rate": 0.0001616816816816817,
|
| 445 |
+
"loss": 0.3779,
|
| 446 |
+
"step": 640
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.95,
|
| 450 |
+
"learning_rate": 0.0001610810810810811,
|
| 451 |
+
"loss": 0.362,
|
| 452 |
+
"step": 650
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.98,
|
| 456 |
+
"learning_rate": 0.00016048048048048047,
|
| 457 |
+
"loss": 0.3427,
|
| 458 |
+
"step": 660
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.01,
|
| 462 |
+
"learning_rate": 0.0001598798798798799,
|
| 463 |
+
"loss": 0.437,
|
| 464 |
+
"step": 670
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.04,
|
| 468 |
+
"learning_rate": 0.00015927927927927927,
|
| 469 |
+
"loss": 0.4169,
|
| 470 |
+
"step": 680
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.07,
|
| 474 |
+
"learning_rate": 0.0001586786786786787,
|
| 475 |
+
"loss": 0.311,
|
| 476 |
+
"step": 690
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.1,
|
| 480 |
+
"learning_rate": 0.00015807807807807807,
|
| 481 |
+
"loss": 0.2802,
|
| 482 |
+
"step": 700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.1,
|
| 486 |
+
"eval_accuracy": 0.9032943676939427,
|
| 487 |
+
"eval_loss": 0.33384454250335693,
|
| 488 |
+
"eval_runtime": 33.4958,
|
| 489 |
+
"eval_samples_per_second": 28.093,
|
| 490 |
+
"eval_steps_per_second": 3.523,
|
| 491 |
+
"step": 700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.13,
|
| 495 |
+
"learning_rate": 0.00015747747747747747,
|
| 496 |
+
"loss": 0.1493,
|
| 497 |
+
"step": 710
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.16,
|
| 501 |
+
"learning_rate": 0.00015687687687687688,
|
| 502 |
+
"loss": 0.272,
|
| 503 |
+
"step": 720
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.19,
|
| 507 |
+
"learning_rate": 0.00015627627627627628,
|
| 508 |
+
"loss": 0.2145,
|
| 509 |
+
"step": 730
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.22,
|
| 513 |
+
"learning_rate": 0.0001556756756756757,
|
| 514 |
+
"loss": 0.1844,
|
| 515 |
+
"step": 740
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.25,
|
| 519 |
+
"learning_rate": 0.00015507507507507508,
|
| 520 |
+
"loss": 0.2618,
|
| 521 |
+
"step": 750
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.28,
|
| 525 |
+
"learning_rate": 0.00015447447447447448,
|
| 526 |
+
"loss": 0.3342,
|
| 527 |
+
"step": 760
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.31,
|
| 531 |
+
"learning_rate": 0.00015387387387387388,
|
| 532 |
+
"loss": 0.3784,
|
| 533 |
+
"step": 770
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.34,
|
| 537 |
+
"learning_rate": 0.00015327327327327328,
|
| 538 |
+
"loss": 0.306,
|
| 539 |
+
"step": 780
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.37,
|
| 543 |
+
"learning_rate": 0.00015267267267267268,
|
| 544 |
+
"loss": 0.3756,
|
| 545 |
+
"step": 790
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.4,
|
| 549 |
+
"learning_rate": 0.00015207207207207208,
|
| 550 |
+
"loss": 0.3014,
|
| 551 |
+
"step": 800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.4,
|
| 555 |
+
"eval_accuracy": 0.8947927736450585,
|
| 556 |
+
"eval_loss": 0.35719022154808044,
|
| 557 |
+
"eval_runtime": 32.3776,
|
| 558 |
+
"eval_samples_per_second": 29.063,
|
| 559 |
+
"eval_steps_per_second": 3.644,
|
| 560 |
+
"step": 800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.43,
|
| 564 |
+
"learning_rate": 0.00015147147147147148,
|
| 565 |
+
"loss": 0.2036,
|
| 566 |
+
"step": 810
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.46,
|
| 570 |
+
"learning_rate": 0.00015087087087087088,
|
| 571 |
+
"loss": 0.239,
|
| 572 |
+
"step": 820
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.49,
|
| 576 |
+
"learning_rate": 0.00015027027027027028,
|
| 577 |
+
"loss": 0.2958,
|
| 578 |
+
"step": 830
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.52,
|
| 582 |
+
"learning_rate": 0.00014966966966966969,
|
| 583 |
+
"loss": 0.3529,
|
| 584 |
+
"step": 840
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.55,
|
| 588 |
+
"learning_rate": 0.0001490690690690691,
|
| 589 |
+
"loss": 0.2531,
|
| 590 |
+
"step": 850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.58,
|
| 594 |
+
"learning_rate": 0.00014846846846846846,
|
| 595 |
+
"loss": 0.2603,
|
| 596 |
+
"step": 860
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.61,
|
| 600 |
+
"learning_rate": 0.0001478678678678679,
|
| 601 |
+
"loss": 0.2643,
|
| 602 |
+
"step": 870
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.64,
|
| 606 |
+
"learning_rate": 0.00014726726726726726,
|
| 607 |
+
"loss": 0.3614,
|
| 608 |
+
"step": 880
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.67,
|
| 612 |
+
"learning_rate": 0.00014666666666666666,
|
| 613 |
+
"loss": 0.1766,
|
| 614 |
+
"step": 890
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.7,
|
| 618 |
+
"learning_rate": 0.00014606606606606606,
|
| 619 |
+
"loss": 0.2508,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.7,
|
| 624 |
+
"eval_accuracy": 0.9022316684378321,
|
| 625 |
+
"eval_loss": 0.34318017959594727,
|
| 626 |
+
"eval_runtime": 32.6394,
|
| 627 |
+
"eval_samples_per_second": 28.83,
|
| 628 |
+
"eval_steps_per_second": 3.615,
|
| 629 |
+
"step": 900
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.73,
|
| 633 |
+
"learning_rate": 0.00014546546546546546,
|
| 634 |
+
"loss": 0.3306,
|
| 635 |
+
"step": 910
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.76,
|
| 639 |
+
"learning_rate": 0.0001448648648648649,
|
| 640 |
+
"loss": 0.2941,
|
| 641 |
+
"step": 920
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.79,
|
| 645 |
+
"learning_rate": 0.00014426426426426427,
|
| 646 |
+
"loss": 0.4128,
|
| 647 |
+
"step": 930
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.82,
|
| 651 |
+
"learning_rate": 0.00014366366366366367,
|
| 652 |
+
"loss": 0.3812,
|
| 653 |
+
"step": 940
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.85,
|
| 657 |
+
"learning_rate": 0.00014306306306306307,
|
| 658 |
+
"loss": 0.2912,
|
| 659 |
+
"step": 950
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.88,
|
| 663 |
+
"learning_rate": 0.00014246246246246247,
|
| 664 |
+
"loss": 0.3563,
|
| 665 |
+
"step": 960
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.91,
|
| 669 |
+
"learning_rate": 0.00014186186186186187,
|
| 670 |
+
"loss": 0.3287,
|
| 671 |
+
"step": 970
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.94,
|
| 675 |
+
"learning_rate": 0.00014126126126126127,
|
| 676 |
+
"loss": 0.4866,
|
| 677 |
+
"step": 980
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.97,
|
| 681 |
+
"learning_rate": 0.00014066066066066067,
|
| 682 |
+
"loss": 0.2232,
|
| 683 |
+
"step": 990
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.0,
|
| 687 |
+
"learning_rate": 0.00014006006006006007,
|
| 688 |
+
"loss": 0.2012,
|
| 689 |
+
"step": 1000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.0,
|
| 693 |
+
"eval_accuracy": 0.9086078639744952,
|
| 694 |
+
"eval_loss": 0.30601173639297485,
|
| 695 |
+
"eval_runtime": 33.0716,
|
| 696 |
+
"eval_samples_per_second": 28.453,
|
| 697 |
+
"eval_steps_per_second": 3.568,
|
| 698 |
+
"step": 1000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.03,
|
| 702 |
+
"learning_rate": 0.00013945945945945947,
|
| 703 |
+
"loss": 0.1947,
|
| 704 |
+
"step": 1010
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.06,
|
| 708 |
+
"learning_rate": 0.00013885885885885887,
|
| 709 |
+
"loss": 0.3934,
|
| 710 |
+
"step": 1020
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.09,
|
| 714 |
+
"learning_rate": 0.00013825825825825827,
|
| 715 |
+
"loss": 0.1187,
|
| 716 |
+
"step": 1030
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.12,
|
| 720 |
+
"learning_rate": 0.00013765765765765765,
|
| 721 |
+
"loss": 0.236,
|
| 722 |
+
"step": 1040
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.15,
|
| 726 |
+
"learning_rate": 0.00013705705705705708,
|
| 727 |
+
"loss": 0.2484,
|
| 728 |
+
"step": 1050
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.18,
|
| 732 |
+
"learning_rate": 0.00013645645645645645,
|
| 733 |
+
"loss": 0.1168,
|
| 734 |
+
"step": 1060
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.21,
|
| 738 |
+
"learning_rate": 0.00013585585585585585,
|
| 739 |
+
"loss": 0.1394,
|
| 740 |
+
"step": 1070
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.24,
|
| 744 |
+
"learning_rate": 0.00013525525525525525,
|
| 745 |
+
"loss": 0.246,
|
| 746 |
+
"step": 1080
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.27,
|
| 750 |
+
"learning_rate": 0.00013465465465465465,
|
| 751 |
+
"loss": 0.3722,
|
| 752 |
+
"step": 1090
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.3,
|
| 756 |
+
"learning_rate": 0.00013405405405405408,
|
| 757 |
+
"loss": 0.2634,
|
| 758 |
+
"step": 1100
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.3,
|
| 762 |
+
"eval_accuracy": 0.9086078639744952,
|
| 763 |
+
"eval_loss": 0.34511974453926086,
|
| 764 |
+
"eval_runtime": 32.7524,
|
| 765 |
+
"eval_samples_per_second": 28.731,
|
| 766 |
+
"eval_steps_per_second": 3.603,
|
| 767 |
+
"step": 1100
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.33,
|
| 771 |
+
"learning_rate": 0.00013345345345345345,
|
| 772 |
+
"loss": 0.2849,
|
| 773 |
+
"step": 1110
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.36,
|
| 777 |
+
"learning_rate": 0.00013285285285285285,
|
| 778 |
+
"loss": 0.165,
|
| 779 |
+
"step": 1120
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.39,
|
| 783 |
+
"learning_rate": 0.00013225225225225226,
|
| 784 |
+
"loss": 0.2819,
|
| 785 |
+
"step": 1130
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.42,
|
| 789 |
+
"learning_rate": 0.00013165165165165166,
|
| 790 |
+
"loss": 0.2486,
|
| 791 |
+
"step": 1140
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 3.45,
|
| 795 |
+
"learning_rate": 0.00013105105105105106,
|
| 796 |
+
"loss": 0.1947,
|
| 797 |
+
"step": 1150
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.48,
|
| 801 |
+
"learning_rate": 0.00013045045045045046,
|
| 802 |
+
"loss": 0.1998,
|
| 803 |
+
"step": 1160
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.51,
|
| 807 |
+
"learning_rate": 0.00012984984984984986,
|
| 808 |
+
"loss": 0.1896,
|
| 809 |
+
"step": 1170
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.54,
|
| 813 |
+
"learning_rate": 0.00012924924924924926,
|
| 814 |
+
"loss": 0.1579,
|
| 815 |
+
"step": 1180
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.57,
|
| 819 |
+
"learning_rate": 0.00012864864864864866,
|
| 820 |
+
"loss": 0.1477,
|
| 821 |
+
"step": 1190
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.6,
|
| 825 |
+
"learning_rate": 0.00012804804804804806,
|
| 826 |
+
"loss": 0.2483,
|
| 827 |
+
"step": 1200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.6,
|
| 831 |
+
"eval_accuracy": 0.9043570669500531,
|
| 832 |
+
"eval_loss": 0.35497206449508667,
|
| 833 |
+
"eval_runtime": 32.9774,
|
| 834 |
+
"eval_samples_per_second": 28.535,
|
| 835 |
+
"eval_steps_per_second": 3.578,
|
| 836 |
+
"step": 1200
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.63,
|
| 840 |
+
"learning_rate": 0.00012744744744744746,
|
| 841 |
+
"loss": 0.2252,
|
| 842 |
+
"step": 1210
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.66,
|
| 846 |
+
"learning_rate": 0.00012684684684684684,
|
| 847 |
+
"loss": 0.1764,
|
| 848 |
+
"step": 1220
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.69,
|
| 852 |
+
"learning_rate": 0.00012624624624624626,
|
| 853 |
+
"loss": 0.2994,
|
| 854 |
+
"step": 1230
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.72,
|
| 858 |
+
"learning_rate": 0.00012564564564564564,
|
| 859 |
+
"loss": 0.2404,
|
| 860 |
+
"step": 1240
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.75,
|
| 864 |
+
"learning_rate": 0.00012504504504504507,
|
| 865 |
+
"loss": 0.1576,
|
| 866 |
+
"step": 1250
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.78,
|
| 870 |
+
"learning_rate": 0.00012444444444444444,
|
| 871 |
+
"loss": 0.1595,
|
| 872 |
+
"step": 1260
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.81,
|
| 876 |
+
"learning_rate": 0.00012384384384384384,
|
| 877 |
+
"loss": 0.2793,
|
| 878 |
+
"step": 1270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.84,
|
| 882 |
+
"learning_rate": 0.00012324324324324327,
|
| 883 |
+
"loss": 0.2766,
|
| 884 |
+
"step": 1280
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.87,
|
| 888 |
+
"learning_rate": 0.00012264264264264264,
|
| 889 |
+
"loss": 0.1626,
|
| 890 |
+
"step": 1290
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.9,
|
| 894 |
+
"learning_rate": 0.00012204204204204204,
|
| 895 |
+
"loss": 0.2273,
|
| 896 |
+
"step": 1300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.9,
|
| 900 |
+
"eval_accuracy": 0.9107332624867163,
|
| 901 |
+
"eval_loss": 0.2977409064769745,
|
| 902 |
+
"eval_runtime": 33.1212,
|
| 903 |
+
"eval_samples_per_second": 28.411,
|
| 904 |
+
"eval_steps_per_second": 3.563,
|
| 905 |
+
"step": 1300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.93,
|
| 909 |
+
"learning_rate": 0.00012144144144144144,
|
| 910 |
+
"loss": 0.3854,
|
| 911 |
+
"step": 1310
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.96,
|
| 915 |
+
"learning_rate": 0.00012084084084084084,
|
| 916 |
+
"loss": 0.326,
|
| 917 |
+
"step": 1320
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.99,
|
| 921 |
+
"learning_rate": 0.00012024024024024026,
|
| 922 |
+
"loss": 0.1902,
|
| 923 |
+
"step": 1330
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.02,
|
| 927 |
+
"learning_rate": 0.00011963963963963965,
|
| 928 |
+
"loss": 0.2819,
|
| 929 |
+
"step": 1340
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.05,
|
| 933 |
+
"learning_rate": 0.00011903903903903903,
|
| 934 |
+
"loss": 0.0952,
|
| 935 |
+
"step": 1350
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.08,
|
| 939 |
+
"learning_rate": 0.00011843843843843845,
|
| 940 |
+
"loss": 0.2189,
|
| 941 |
+
"step": 1360
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.11,
|
| 945 |
+
"learning_rate": 0.00011783783783783784,
|
| 946 |
+
"loss": 0.1538,
|
| 947 |
+
"step": 1370
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.14,
|
| 951 |
+
"learning_rate": 0.00011723723723723725,
|
| 952 |
+
"loss": 0.292,
|
| 953 |
+
"step": 1380
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.17,
|
| 957 |
+
"learning_rate": 0.00011663663663663664,
|
| 958 |
+
"loss": 0.1944,
|
| 959 |
+
"step": 1390
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.2,
|
| 963 |
+
"learning_rate": 0.00011603603603603604,
|
| 964 |
+
"loss": 0.1214,
|
| 965 |
+
"step": 1400
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 4.2,
|
| 969 |
+
"eval_accuracy": 0.9160467587672688,
|
| 970 |
+
"eval_loss": 0.3265420198440552,
|
| 971 |
+
"eval_runtime": 32.8927,
|
| 972 |
+
"eval_samples_per_second": 28.608,
|
| 973 |
+
"eval_steps_per_second": 3.587,
|
| 974 |
+
"step": 1400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.23,
|
| 978 |
+
"learning_rate": 0.00011543543543543545,
|
| 979 |
+
"loss": 0.1619,
|
| 980 |
+
"step": 1410
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 4.26,
|
| 984 |
+
"learning_rate": 0.00011483483483483484,
|
| 985 |
+
"loss": 0.1994,
|
| 986 |
+
"step": 1420
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 4.29,
|
| 990 |
+
"learning_rate": 0.00011423423423423425,
|
| 991 |
+
"loss": 0.1492,
|
| 992 |
+
"step": 1430
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.32,
|
| 996 |
+
"learning_rate": 0.00011363363363363364,
|
| 997 |
+
"loss": 0.185,
|
| 998 |
+
"step": 1440
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.35,
|
| 1002 |
+
"learning_rate": 0.00011303303303303303,
|
| 1003 |
+
"loss": 0.096,
|
| 1004 |
+
"step": 1450
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.38,
|
| 1008 |
+
"learning_rate": 0.00011243243243243244,
|
| 1009 |
+
"loss": 0.2023,
|
| 1010 |
+
"step": 1460
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.41,
|
| 1014 |
+
"learning_rate": 0.00011183183183183183,
|
| 1015 |
+
"loss": 0.172,
|
| 1016 |
+
"step": 1470
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 4.44,
|
| 1020 |
+
"learning_rate": 0.00011123123123123123,
|
| 1021 |
+
"loss": 0.2173,
|
| 1022 |
+
"step": 1480
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 4.47,
|
| 1026 |
+
"learning_rate": 0.00011063063063063063,
|
| 1027 |
+
"loss": 0.1906,
|
| 1028 |
+
"step": 1490
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.5,
|
| 1032 |
+
"learning_rate": 0.00011003003003003003,
|
| 1033 |
+
"loss": 0.2048,
|
| 1034 |
+
"step": 1500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.5,
|
| 1038 |
+
"eval_accuracy": 0.9213602550478215,
|
| 1039 |
+
"eval_loss": 0.31257954239845276,
|
| 1040 |
+
"eval_runtime": 33.0709,
|
| 1041 |
+
"eval_samples_per_second": 28.454,
|
| 1042 |
+
"eval_steps_per_second": 3.568,
|
| 1043 |
+
"step": 1500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.53,
|
| 1047 |
+
"learning_rate": 0.00010942942942942945,
|
| 1048 |
+
"loss": 0.1993,
|
| 1049 |
+
"step": 1510
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.56,
|
| 1053 |
+
"learning_rate": 0.00010882882882882883,
|
| 1054 |
+
"loss": 0.2563,
|
| 1055 |
+
"step": 1520
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 4.59,
|
| 1059 |
+
"learning_rate": 0.00010822822822822822,
|
| 1060 |
+
"loss": 0.1404,
|
| 1061 |
+
"step": 1530
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 4.62,
|
| 1065 |
+
"learning_rate": 0.00010762762762762764,
|
| 1066 |
+
"loss": 0.3455,
|
| 1067 |
+
"step": 1540
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 4.65,
|
| 1071 |
+
"learning_rate": 0.00010702702702702702,
|
| 1072 |
+
"loss": 0.1722,
|
| 1073 |
+
"step": 1550
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.68,
|
| 1077 |
+
"learning_rate": 0.00010642642642642644,
|
| 1078 |
+
"loss": 0.2154,
|
| 1079 |
+
"step": 1560
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 4.71,
|
| 1083 |
+
"learning_rate": 0.00010582582582582582,
|
| 1084 |
+
"loss": 0.1499,
|
| 1085 |
+
"step": 1570
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 4.74,
|
| 1089 |
+
"learning_rate": 0.00010522522522522523,
|
| 1090 |
+
"loss": 0.106,
|
| 1091 |
+
"step": 1580
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 4.77,
|
| 1095 |
+
"learning_rate": 0.00010462462462462464,
|
| 1096 |
+
"loss": 0.0827,
|
| 1097 |
+
"step": 1590
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.8,
|
| 1101 |
+
"learning_rate": 0.00010402402402402403,
|
| 1102 |
+
"loss": 0.0997,
|
| 1103 |
+
"step": 1600
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 4.8,
|
| 1107 |
+
"eval_accuracy": 0.9160467587672688,
|
| 1108 |
+
"eval_loss": 0.3163708448410034,
|
| 1109 |
+
"eval_runtime": 32.9295,
|
| 1110 |
+
"eval_samples_per_second": 28.576,
|
| 1111 |
+
"eval_steps_per_second": 3.583,
|
| 1112 |
+
"step": 1600
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.83,
|
| 1116 |
+
"learning_rate": 0.00010342342342342344,
|
| 1117 |
+
"loss": 0.2504,
|
| 1118 |
+
"step": 1610
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.86,
|
| 1122 |
+
"learning_rate": 0.00010282282282282283,
|
| 1123 |
+
"loss": 0.156,
|
| 1124 |
+
"step": 1620
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.89,
|
| 1128 |
+
"learning_rate": 0.00010222222222222222,
|
| 1129 |
+
"loss": 0.1835,
|
| 1130 |
+
"step": 1630
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.92,
|
| 1134 |
+
"learning_rate": 0.00010162162162162163,
|
| 1135 |
+
"loss": 0.2362,
|
| 1136 |
+
"step": 1640
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.95,
|
| 1140 |
+
"learning_rate": 0.00010102102102102102,
|
| 1141 |
+
"loss": 0.1598,
|
| 1142 |
+
"step": 1650
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.98,
|
| 1146 |
+
"learning_rate": 0.00010042042042042043,
|
| 1147 |
+
"loss": 0.1116,
|
| 1148 |
+
"step": 1660
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 5.02,
|
| 1152 |
+
"learning_rate": 9.981981981981983e-05,
|
| 1153 |
+
"loss": 0.0431,
|
| 1154 |
+
"step": 1670
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 5.05,
|
| 1158 |
+
"learning_rate": 9.921921921921923e-05,
|
| 1159 |
+
"loss": 0.2061,
|
| 1160 |
+
"step": 1680
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 5.08,
|
| 1164 |
+
"learning_rate": 9.861861861861862e-05,
|
| 1165 |
+
"loss": 0.117,
|
| 1166 |
+
"step": 1690
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 5.11,
|
| 1170 |
+
"learning_rate": 9.801801801801802e-05,
|
| 1171 |
+
"loss": 0.1145,
|
| 1172 |
+
"step": 1700
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 5.11,
|
| 1176 |
+
"eval_accuracy": 0.9139213602550478,
|
| 1177 |
+
"eval_loss": 0.30551373958587646,
|
| 1178 |
+
"eval_runtime": 32.9051,
|
| 1179 |
+
"eval_samples_per_second": 28.597,
|
| 1180 |
+
"eval_steps_per_second": 3.586,
|
| 1181 |
+
"step": 1700
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 5.14,
|
| 1185 |
+
"learning_rate": 9.741741741741742e-05,
|
| 1186 |
+
"loss": 0.1235,
|
| 1187 |
+
"step": 1710
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 5.17,
|
| 1191 |
+
"learning_rate": 9.681681681681682e-05,
|
| 1192 |
+
"loss": 0.0922,
|
| 1193 |
+
"step": 1720
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 5.2,
|
| 1197 |
+
"learning_rate": 9.621621621621622e-05,
|
| 1198 |
+
"loss": 0.2855,
|
| 1199 |
+
"step": 1730
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 5.23,
|
| 1203 |
+
"learning_rate": 9.561561561561561e-05,
|
| 1204 |
+
"loss": 0.1353,
|
| 1205 |
+
"step": 1740
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 5.26,
|
| 1209 |
+
"learning_rate": 9.501501501501501e-05,
|
| 1210 |
+
"loss": 0.098,
|
| 1211 |
+
"step": 1750
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 5.29,
|
| 1215 |
+
"learning_rate": 9.441441441441443e-05,
|
| 1216 |
+
"loss": 0.1862,
|
| 1217 |
+
"step": 1760
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 5.32,
|
| 1221 |
+
"learning_rate": 9.381381381381383e-05,
|
| 1222 |
+
"loss": 0.2086,
|
| 1223 |
+
"step": 1770
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 5.35,
|
| 1227 |
+
"learning_rate": 9.321321321321322e-05,
|
| 1228 |
+
"loss": 0.1683,
|
| 1229 |
+
"step": 1780
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 5.38,
|
| 1233 |
+
"learning_rate": 9.261261261261262e-05,
|
| 1234 |
+
"loss": 0.1101,
|
| 1235 |
+
"step": 1790
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 5.41,
|
| 1239 |
+
"learning_rate": 9.201201201201202e-05,
|
| 1240 |
+
"loss": 0.1578,
|
| 1241 |
+
"step": 1800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 5.41,
|
| 1245 |
+
"eval_accuracy": 0.9171094580233794,
|
| 1246 |
+
"eval_loss": 0.3195084035396576,
|
| 1247 |
+
"eval_runtime": 33.6527,
|
| 1248 |
+
"eval_samples_per_second": 27.962,
|
| 1249 |
+
"eval_steps_per_second": 3.506,
|
| 1250 |
+
"step": 1800
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 5.44,
|
| 1254 |
+
"learning_rate": 9.141141141141142e-05,
|
| 1255 |
+
"loss": 0.2522,
|
| 1256 |
+
"step": 1810
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 5.47,
|
| 1260 |
+
"learning_rate": 9.081081081081082e-05,
|
| 1261 |
+
"loss": 0.0995,
|
| 1262 |
+
"step": 1820
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 5.5,
|
| 1266 |
+
"learning_rate": 9.02102102102102e-05,
|
| 1267 |
+
"loss": 0.1168,
|
| 1268 |
+
"step": 1830
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 5.53,
|
| 1272 |
+
"learning_rate": 8.96096096096096e-05,
|
| 1273 |
+
"loss": 0.17,
|
| 1274 |
+
"step": 1840
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 5.56,
|
| 1278 |
+
"learning_rate": 8.900900900900902e-05,
|
| 1279 |
+
"loss": 0.0545,
|
| 1280 |
+
"step": 1850
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 5.59,
|
| 1284 |
+
"learning_rate": 8.840840840840842e-05,
|
| 1285 |
+
"loss": 0.1607,
|
| 1286 |
+
"step": 1860
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 5.62,
|
| 1290 |
+
"learning_rate": 8.780780780780781e-05,
|
| 1291 |
+
"loss": 0.0549,
|
| 1292 |
+
"step": 1870
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 5.65,
|
| 1296 |
+
"learning_rate": 8.720720720720721e-05,
|
| 1297 |
+
"loss": 0.1503,
|
| 1298 |
+
"step": 1880
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 5.68,
|
| 1302 |
+
"learning_rate": 8.660660660660661e-05,
|
| 1303 |
+
"loss": 0.2044,
|
| 1304 |
+
"step": 1890
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 5.71,
|
| 1308 |
+
"learning_rate": 8.600600600600601e-05,
|
| 1309 |
+
"loss": 0.0615,
|
| 1310 |
+
"step": 1900
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 5.71,
|
| 1314 |
+
"eval_accuracy": 0.9107332624867163,
|
| 1315 |
+
"eval_loss": 0.3401225805282593,
|
| 1316 |
+
"eval_runtime": 33.1832,
|
| 1317 |
+
"eval_samples_per_second": 28.358,
|
| 1318 |
+
"eval_steps_per_second": 3.556,
|
| 1319 |
+
"step": 1900
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 5.74,
|
| 1323 |
+
"learning_rate": 8.540540540540541e-05,
|
| 1324 |
+
"loss": 0.1611,
|
| 1325 |
+
"step": 1910
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 5.77,
|
| 1329 |
+
"learning_rate": 8.48048048048048e-05,
|
| 1330 |
+
"loss": 0.1693,
|
| 1331 |
+
"step": 1920
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 5.8,
|
| 1335 |
+
"learning_rate": 8.42042042042042e-05,
|
| 1336 |
+
"loss": 0.079,
|
| 1337 |
+
"step": 1930
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 5.83,
|
| 1341 |
+
"learning_rate": 8.360360360360362e-05,
|
| 1342 |
+
"loss": 0.2182,
|
| 1343 |
+
"step": 1940
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 5.86,
|
| 1347 |
+
"learning_rate": 8.300300300300302e-05,
|
| 1348 |
+
"loss": 0.2156,
|
| 1349 |
+
"step": 1950
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 5.89,
|
| 1353 |
+
"learning_rate": 8.24024024024024e-05,
|
| 1354 |
+
"loss": 0.1422,
|
| 1355 |
+
"step": 1960
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 5.92,
|
| 1359 |
+
"learning_rate": 8.18018018018018e-05,
|
| 1360 |
+
"loss": 0.1465,
|
| 1361 |
+
"step": 1970
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 5.95,
|
| 1365 |
+
"learning_rate": 8.12012012012012e-05,
|
| 1366 |
+
"loss": 0.2347,
|
| 1367 |
+
"step": 1980
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 5.98,
|
| 1371 |
+
"learning_rate": 8.06006006006006e-05,
|
| 1372 |
+
"loss": 0.1994,
|
| 1373 |
+
"step": 1990
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 6.01,
|
| 1377 |
+
"learning_rate": 8e-05,
|
| 1378 |
+
"loss": 0.1537,
|
| 1379 |
+
"step": 2000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 6.01,
|
| 1383 |
+
"eval_accuracy": 0.9096705632306057,
|
| 1384 |
+
"eval_loss": 0.3427741527557373,
|
| 1385 |
+
"eval_runtime": 33.1728,
|
| 1386 |
+
"eval_samples_per_second": 28.367,
|
| 1387 |
+
"eval_steps_per_second": 3.557,
|
| 1388 |
+
"step": 2000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 6.04,
|
| 1392 |
+
"learning_rate": 7.93993993993994e-05,
|
| 1393 |
+
"loss": 0.1196,
|
| 1394 |
+
"step": 2010
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 6.07,
|
| 1398 |
+
"learning_rate": 7.87987987987988e-05,
|
| 1399 |
+
"loss": 0.1979,
|
| 1400 |
+
"step": 2020
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 6.1,
|
| 1404 |
+
"learning_rate": 7.819819819819821e-05,
|
| 1405 |
+
"loss": 0.123,
|
| 1406 |
+
"step": 2030
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 6.13,
|
| 1410 |
+
"learning_rate": 7.759759759759761e-05,
|
| 1411 |
+
"loss": 0.1802,
|
| 1412 |
+
"step": 2040
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 6.16,
|
| 1416 |
+
"learning_rate": 7.699699699699701e-05,
|
| 1417 |
+
"loss": 0.1126,
|
| 1418 |
+
"step": 2050
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 6.19,
|
| 1422 |
+
"learning_rate": 7.63963963963964e-05,
|
| 1423 |
+
"loss": 0.1223,
|
| 1424 |
+
"step": 2060
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 6.22,
|
| 1428 |
+
"learning_rate": 7.57957957957958e-05,
|
| 1429 |
+
"loss": 0.1536,
|
| 1430 |
+
"step": 2070
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 6.25,
|
| 1434 |
+
"learning_rate": 7.51951951951952e-05,
|
| 1435 |
+
"loss": 0.0856,
|
| 1436 |
+
"step": 2080
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 6.28,
|
| 1440 |
+
"learning_rate": 7.45945945945946e-05,
|
| 1441 |
+
"loss": 0.0928,
|
| 1442 |
+
"step": 2090
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 6.31,
|
| 1446 |
+
"learning_rate": 7.399399399399399e-05,
|
| 1447 |
+
"loss": 0.1278,
|
| 1448 |
+
"step": 2100
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 6.31,
|
| 1452 |
+
"eval_accuracy": 0.9192348565356004,
|
| 1453 |
+
"eval_loss": 0.3057916462421417,
|
| 1454 |
+
"eval_runtime": 32.9085,
|
| 1455 |
+
"eval_samples_per_second": 28.594,
|
| 1456 |
+
"eval_steps_per_second": 3.586,
|
| 1457 |
+
"step": 2100
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 6.34,
|
| 1461 |
+
"learning_rate": 7.339339339339339e-05,
|
| 1462 |
+
"loss": 0.1626,
|
| 1463 |
+
"step": 2110
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 6.37,
|
| 1467 |
+
"learning_rate": 7.27927927927928e-05,
|
| 1468 |
+
"loss": 0.1518,
|
| 1469 |
+
"step": 2120
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 6.4,
|
| 1473 |
+
"learning_rate": 7.21921921921922e-05,
|
| 1474 |
+
"loss": 0.1275,
|
| 1475 |
+
"step": 2130
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 6.43,
|
| 1479 |
+
"learning_rate": 7.15915915915916e-05,
|
| 1480 |
+
"loss": 0.1691,
|
| 1481 |
+
"step": 2140
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 6.46,
|
| 1485 |
+
"learning_rate": 7.099099099099099e-05,
|
| 1486 |
+
"loss": 0.0378,
|
| 1487 |
+
"step": 2150
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 6.49,
|
| 1491 |
+
"learning_rate": 7.039039039039039e-05,
|
| 1492 |
+
"loss": 0.0721,
|
| 1493 |
+
"step": 2160
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 6.52,
|
| 1497 |
+
"learning_rate": 6.97897897897898e-05,
|
| 1498 |
+
"loss": 0.116,
|
| 1499 |
+
"step": 2170
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 6.55,
|
| 1503 |
+
"learning_rate": 6.91891891891892e-05,
|
| 1504 |
+
"loss": 0.0625,
|
| 1505 |
+
"step": 2180
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 6.58,
|
| 1509 |
+
"learning_rate": 6.858858858858858e-05,
|
| 1510 |
+
"loss": 0.0699,
|
| 1511 |
+
"step": 2190
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 6.61,
|
| 1515 |
+
"learning_rate": 6.798798798798798e-05,
|
| 1516 |
+
"loss": 0.1274,
|
| 1517 |
+
"step": 2200
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 6.61,
|
| 1521 |
+
"eval_accuracy": 0.9192348565356004,
|
| 1522 |
+
"eval_loss": 0.3189365565776825,
|
| 1523 |
+
"eval_runtime": 32.9229,
|
| 1524 |
+
"eval_samples_per_second": 28.582,
|
| 1525 |
+
"eval_steps_per_second": 3.584,
|
| 1526 |
+
"step": 2200
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 6.64,
|
| 1530 |
+
"learning_rate": 6.73873873873874e-05,
|
| 1531 |
+
"loss": 0.0926,
|
| 1532 |
+
"step": 2210
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 6.67,
|
| 1536 |
+
"learning_rate": 6.67867867867868e-05,
|
| 1537 |
+
"loss": 0.0402,
|
| 1538 |
+
"step": 2220
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 6.7,
|
| 1542 |
+
"learning_rate": 6.61861861861862e-05,
|
| 1543 |
+
"loss": 0.2149,
|
| 1544 |
+
"step": 2230
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 6.73,
|
| 1548 |
+
"learning_rate": 6.558558558558559e-05,
|
| 1549 |
+
"loss": 0.2664,
|
| 1550 |
+
"step": 2240
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 6.76,
|
| 1554 |
+
"learning_rate": 6.498498498498499e-05,
|
| 1555 |
+
"loss": 0.1215,
|
| 1556 |
+
"step": 2250
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 6.79,
|
| 1560 |
+
"learning_rate": 6.438438438438439e-05,
|
| 1561 |
+
"loss": 0.0846,
|
| 1562 |
+
"step": 2260
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 6.82,
|
| 1566 |
+
"learning_rate": 6.378378378378379e-05,
|
| 1567 |
+
"loss": 0.0453,
|
| 1568 |
+
"step": 2270
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 6.85,
|
| 1572 |
+
"learning_rate": 6.318318318318318e-05,
|
| 1573 |
+
"loss": 0.122,
|
| 1574 |
+
"step": 2280
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 6.88,
|
| 1578 |
+
"learning_rate": 6.258258258258258e-05,
|
| 1579 |
+
"loss": 0.2334,
|
| 1580 |
+
"step": 2290
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 6.91,
|
| 1584 |
+
"learning_rate": 6.198198198198199e-05,
|
| 1585 |
+
"loss": 0.0877,
|
| 1586 |
+
"step": 2300
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 6.91,
|
| 1590 |
+
"eval_accuracy": 0.9181721572794899,
|
| 1591 |
+
"eval_loss": 0.33698955178260803,
|
| 1592 |
+
"eval_runtime": 33.8365,
|
| 1593 |
+
"eval_samples_per_second": 27.81,
|
| 1594 |
+
"eval_steps_per_second": 3.487,
|
| 1595 |
+
"step": 2300
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 6.94,
|
| 1599 |
+
"learning_rate": 6.138138138138139e-05,
|
| 1600 |
+
"loss": 0.1992,
|
| 1601 |
+
"step": 2310
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 6.97,
|
| 1605 |
+
"learning_rate": 6.0780780780780786e-05,
|
| 1606 |
+
"loss": 0.1207,
|
| 1607 |
+
"step": 2320
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 7.0,
|
| 1611 |
+
"learning_rate": 6.018018018018018e-05,
|
| 1612 |
+
"loss": 0.231,
|
| 1613 |
+
"step": 2330
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 7.03,
|
| 1617 |
+
"learning_rate": 5.957957957957958e-05,
|
| 1618 |
+
"loss": 0.0674,
|
| 1619 |
+
"step": 2340
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 7.06,
|
| 1623 |
+
"learning_rate": 5.897897897897898e-05,
|
| 1624 |
+
"loss": 0.0818,
|
| 1625 |
+
"step": 2350
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 7.09,
|
| 1629 |
+
"learning_rate": 5.837837837837838e-05,
|
| 1630 |
+
"loss": 0.2289,
|
| 1631 |
+
"step": 2360
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 7.12,
|
| 1635 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 1636 |
+
"loss": 0.0863,
|
| 1637 |
+
"step": 2370
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 7.15,
|
| 1641 |
+
"learning_rate": 5.717717717717718e-05,
|
| 1642 |
+
"loss": 0.1641,
|
| 1643 |
+
"step": 2380
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 7.18,
|
| 1647 |
+
"learning_rate": 5.657657657657658e-05,
|
| 1648 |
+
"loss": 0.0895,
|
| 1649 |
+
"step": 2390
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 7.21,
|
| 1653 |
+
"learning_rate": 5.597597597597598e-05,
|
| 1654 |
+
"loss": 0.1058,
|
| 1655 |
+
"step": 2400
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 7.21,
|
| 1659 |
+
"eval_accuracy": 0.9192348565356004,
|
| 1660 |
+
"eval_loss": 0.3225291967391968,
|
| 1661 |
+
"eval_runtime": 33.1868,
|
| 1662 |
+
"eval_samples_per_second": 28.355,
|
| 1663 |
+
"eval_steps_per_second": 3.556,
|
| 1664 |
+
"step": 2400
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 7.24,
|
| 1668 |
+
"learning_rate": 5.537537537537538e-05,
|
| 1669 |
+
"loss": 0.0884,
|
| 1670 |
+
"step": 2410
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 7.27,
|
| 1674 |
+
"learning_rate": 5.4774774774774774e-05,
|
| 1675 |
+
"loss": 0.1579,
|
| 1676 |
+
"step": 2420
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 7.3,
|
| 1680 |
+
"learning_rate": 5.4174174174174175e-05,
|
| 1681 |
+
"loss": 0.071,
|
| 1682 |
+
"step": 2430
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 7.33,
|
| 1686 |
+
"learning_rate": 5.3573573573573576e-05,
|
| 1687 |
+
"loss": 0.0217,
|
| 1688 |
+
"step": 2440
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 7.36,
|
| 1692 |
+
"learning_rate": 5.2972972972972976e-05,
|
| 1693 |
+
"loss": 0.0931,
|
| 1694 |
+
"step": 2450
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 7.39,
|
| 1698 |
+
"learning_rate": 5.237237237237238e-05,
|
| 1699 |
+
"loss": 0.1673,
|
| 1700 |
+
"step": 2460
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 7.42,
|
| 1704 |
+
"learning_rate": 5.177177177177177e-05,
|
| 1705 |
+
"loss": 0.1473,
|
| 1706 |
+
"step": 2470
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 7.45,
|
| 1710 |
+
"learning_rate": 5.117117117117117e-05,
|
| 1711 |
+
"loss": 0.1578,
|
| 1712 |
+
"step": 2480
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 7.48,
|
| 1716 |
+
"learning_rate": 5.063063063063064e-05,
|
| 1717 |
+
"loss": 0.1114,
|
| 1718 |
+
"step": 2490
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 7.51,
|
| 1722 |
+
"learning_rate": 5.003003003003003e-05,
|
| 1723 |
+
"loss": 0.1742,
|
| 1724 |
+
"step": 2500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 7.51,
|
| 1728 |
+
"eval_accuracy": 0.9213602550478215,
|
| 1729 |
+
"eval_loss": 0.3341035842895508,
|
| 1730 |
+
"eval_runtime": 33.4101,
|
| 1731 |
+
"eval_samples_per_second": 28.165,
|
| 1732 |
+
"eval_steps_per_second": 3.532,
|
| 1733 |
+
"step": 2500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 7.54,
|
| 1737 |
+
"learning_rate": 4.942942942942943e-05,
|
| 1738 |
+
"loss": 0.12,
|
| 1739 |
+
"step": 2510
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 7.57,
|
| 1743 |
+
"learning_rate": 4.882882882882883e-05,
|
| 1744 |
+
"loss": 0.1414,
|
| 1745 |
+
"step": 2520
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 7.6,
|
| 1749 |
+
"learning_rate": 4.822822822822823e-05,
|
| 1750 |
+
"loss": 0.1844,
|
| 1751 |
+
"step": 2530
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 7.63,
|
| 1755 |
+
"learning_rate": 4.762762762762763e-05,
|
| 1756 |
+
"loss": 0.1866,
|
| 1757 |
+
"step": 2540
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 7.66,
|
| 1761 |
+
"learning_rate": 4.7027027027027035e-05,
|
| 1762 |
+
"loss": 0.2651,
|
| 1763 |
+
"step": 2550
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 7.69,
|
| 1767 |
+
"learning_rate": 4.642642642642643e-05,
|
| 1768 |
+
"loss": 0.0861,
|
| 1769 |
+
"step": 2560
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 7.72,
|
| 1773 |
+
"learning_rate": 4.582582582582583e-05,
|
| 1774 |
+
"loss": 0.0685,
|
| 1775 |
+
"step": 2570
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 7.75,
|
| 1779 |
+
"learning_rate": 4.5225225225225224e-05,
|
| 1780 |
+
"loss": 0.0992,
|
| 1781 |
+
"step": 2580
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 7.78,
|
| 1785 |
+
"learning_rate": 4.4624624624624625e-05,
|
| 1786 |
+
"loss": 0.051,
|
| 1787 |
+
"step": 2590
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 7.81,
|
| 1791 |
+
"learning_rate": 4.4024024024024026e-05,
|
| 1792 |
+
"loss": 0.0949,
|
| 1793 |
+
"step": 2600
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 7.81,
|
| 1797 |
+
"eval_accuracy": 0.9256110520722636,
|
| 1798 |
+
"eval_loss": 0.3125704526901245,
|
| 1799 |
+
"eval_runtime": 33.5498,
|
| 1800 |
+
"eval_samples_per_second": 28.048,
|
| 1801 |
+
"eval_steps_per_second": 3.517,
|
| 1802 |
+
"step": 2600
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 7.84,
|
| 1806 |
+
"learning_rate": 4.342342342342343e-05,
|
| 1807 |
+
"loss": 0.0721,
|
| 1808 |
+
"step": 2610
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 7.87,
|
| 1812 |
+
"learning_rate": 4.282282282282282e-05,
|
| 1813 |
+
"loss": 0.2377,
|
| 1814 |
+
"step": 2620
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 7.9,
|
| 1818 |
+
"learning_rate": 4.222222222222222e-05,
|
| 1819 |
+
"loss": 0.1324,
|
| 1820 |
+
"step": 2630
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 7.93,
|
| 1824 |
+
"learning_rate": 4.162162162162163e-05,
|
| 1825 |
+
"loss": 0.1696,
|
| 1826 |
+
"step": 2640
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 7.96,
|
| 1830 |
+
"learning_rate": 4.102102102102102e-05,
|
| 1831 |
+
"loss": 0.1086,
|
| 1832 |
+
"step": 2650
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 7.99,
|
| 1836 |
+
"learning_rate": 4.0420420420420424e-05,
|
| 1837 |
+
"loss": 0.2007,
|
| 1838 |
+
"step": 2660
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 8.02,
|
| 1842 |
+
"learning_rate": 3.981981981981982e-05,
|
| 1843 |
+
"loss": 0.1377,
|
| 1844 |
+
"step": 2670
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 8.05,
|
| 1848 |
+
"learning_rate": 3.921921921921922e-05,
|
| 1849 |
+
"loss": 0.0684,
|
| 1850 |
+
"step": 2680
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 8.08,
|
| 1854 |
+
"learning_rate": 3.861861861861862e-05,
|
| 1855 |
+
"loss": 0.0386,
|
| 1856 |
+
"step": 2690
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 8.11,
|
| 1860 |
+
"learning_rate": 3.801801801801802e-05,
|
| 1861 |
+
"loss": 0.1732,
|
| 1862 |
+
"step": 2700
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 8.11,
|
| 1866 |
+
"eval_accuracy": 0.9234856535600425,
|
| 1867 |
+
"eval_loss": 0.30780139565467834,
|
| 1868 |
+
"eval_runtime": 32.9779,
|
| 1869 |
+
"eval_samples_per_second": 28.534,
|
| 1870 |
+
"eval_steps_per_second": 3.578,
|
| 1871 |
+
"step": 2700
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 8.14,
|
| 1875 |
+
"learning_rate": 3.741741741741742e-05,
|
| 1876 |
+
"loss": 0.0642,
|
| 1877 |
+
"step": 2710
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 8.17,
|
| 1881 |
+
"learning_rate": 3.6816816816816816e-05,
|
| 1882 |
+
"loss": 0.16,
|
| 1883 |
+
"step": 2720
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 8.2,
|
| 1887 |
+
"learning_rate": 3.621621621621622e-05,
|
| 1888 |
+
"loss": 0.0922,
|
| 1889 |
+
"step": 2730
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 8.23,
|
| 1893 |
+
"learning_rate": 3.561561561561562e-05,
|
| 1894 |
+
"loss": 0.0865,
|
| 1895 |
+
"step": 2740
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 8.26,
|
| 1899 |
+
"learning_rate": 3.501501501501502e-05,
|
| 1900 |
+
"loss": 0.1227,
|
| 1901 |
+
"step": 2750
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 8.29,
|
| 1905 |
+
"learning_rate": 3.441441441441441e-05,
|
| 1906 |
+
"loss": 0.0769,
|
| 1907 |
+
"step": 2760
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 8.32,
|
| 1911 |
+
"learning_rate": 3.381381381381381e-05,
|
| 1912 |
+
"loss": 0.1192,
|
| 1913 |
+
"step": 2770
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 8.35,
|
| 1917 |
+
"learning_rate": 3.3213213213213214e-05,
|
| 1918 |
+
"loss": 0.1045,
|
| 1919 |
+
"step": 2780
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 8.38,
|
| 1923 |
+
"learning_rate": 3.2612612612612615e-05,
|
| 1924 |
+
"loss": 0.1013,
|
| 1925 |
+
"step": 2790
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 8.41,
|
| 1929 |
+
"learning_rate": 3.2012012012012015e-05,
|
| 1930 |
+
"loss": 0.0894,
|
| 1931 |
+
"step": 2800
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 8.41,
|
| 1935 |
+
"eval_accuracy": 0.926673751328374,
|
| 1936 |
+
"eval_loss": 0.30979347229003906,
|
| 1937 |
+
"eval_runtime": 33.3735,
|
| 1938 |
+
"eval_samples_per_second": 28.196,
|
| 1939 |
+
"eval_steps_per_second": 3.536,
|
| 1940 |
+
"step": 2800
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 8.44,
|
| 1944 |
+
"learning_rate": 3.141141141141141e-05,
|
| 1945 |
+
"loss": 0.0846,
|
| 1946 |
+
"step": 2810
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 8.47,
|
| 1950 |
+
"learning_rate": 3.081081081081082e-05,
|
| 1951 |
+
"loss": 0.0786,
|
| 1952 |
+
"step": 2820
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 8.5,
|
| 1956 |
+
"learning_rate": 3.021021021021021e-05,
|
| 1957 |
+
"loss": 0.1076,
|
| 1958 |
+
"step": 2830
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 8.53,
|
| 1962 |
+
"learning_rate": 2.9609609609609612e-05,
|
| 1963 |
+
"loss": 0.0685,
|
| 1964 |
+
"step": 2840
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 8.56,
|
| 1968 |
+
"learning_rate": 2.900900900900901e-05,
|
| 1969 |
+
"loss": 0.0529,
|
| 1970 |
+
"step": 2850
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 8.59,
|
| 1974 |
+
"learning_rate": 2.840840840840841e-05,
|
| 1975 |
+
"loss": 0.1153,
|
| 1976 |
+
"step": 2860
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 8.62,
|
| 1980 |
+
"learning_rate": 2.7807807807807808e-05,
|
| 1981 |
+
"loss": 0.0839,
|
| 1982 |
+
"step": 2870
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 8.65,
|
| 1986 |
+
"learning_rate": 2.720720720720721e-05,
|
| 1987 |
+
"loss": 0.0996,
|
| 1988 |
+
"step": 2880
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 8.68,
|
| 1992 |
+
"learning_rate": 2.660660660660661e-05,
|
| 1993 |
+
"loss": 0.1005,
|
| 1994 |
+
"step": 2890
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 8.71,
|
| 1998 |
+
"learning_rate": 2.6006006006006007e-05,
|
| 1999 |
+
"loss": 0.1257,
|
| 2000 |
+
"step": 2900
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 8.71,
|
| 2004 |
+
"eval_accuracy": 0.9319872476089267,
|
| 2005 |
+
"eval_loss": 0.30299508571624756,
|
| 2006 |
+
"eval_runtime": 33.1081,
|
| 2007 |
+
"eval_samples_per_second": 28.422,
|
| 2008 |
+
"eval_steps_per_second": 3.564,
|
| 2009 |
+
"step": 2900
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 8.74,
|
| 2013 |
+
"learning_rate": 2.5405405405405408e-05,
|
| 2014 |
+
"loss": 0.16,
|
| 2015 |
+
"step": 2910
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 8.77,
|
| 2019 |
+
"learning_rate": 2.480480480480481e-05,
|
| 2020 |
+
"loss": 0.1078,
|
| 2021 |
+
"step": 2920
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 8.8,
|
| 2025 |
+
"learning_rate": 2.4204204204204206e-05,
|
| 2026 |
+
"loss": 0.0802,
|
| 2027 |
+
"step": 2930
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 8.83,
|
| 2031 |
+
"learning_rate": 2.3603603603603607e-05,
|
| 2032 |
+
"loss": 0.0342,
|
| 2033 |
+
"step": 2940
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 8.86,
|
| 2037 |
+
"learning_rate": 2.3003003003003004e-05,
|
| 2038 |
+
"loss": 0.2069,
|
| 2039 |
+
"step": 2950
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 8.89,
|
| 2043 |
+
"learning_rate": 2.24024024024024e-05,
|
| 2044 |
+
"loss": 0.0605,
|
| 2045 |
+
"step": 2960
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 8.92,
|
| 2049 |
+
"learning_rate": 2.1801801801801803e-05,
|
| 2050 |
+
"loss": 0.1067,
|
| 2051 |
+
"step": 2970
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 8.95,
|
| 2055 |
+
"learning_rate": 2.12012012012012e-05,
|
| 2056 |
+
"loss": 0.0894,
|
| 2057 |
+
"step": 2980
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 8.98,
|
| 2061 |
+
"learning_rate": 2.06006006006006e-05,
|
| 2062 |
+
"loss": 0.0995,
|
| 2063 |
+
"step": 2990
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 9.01,
|
| 2067 |
+
"learning_rate": 2e-05,
|
| 2068 |
+
"loss": 0.1747,
|
| 2069 |
+
"step": 3000
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 9.01,
|
| 2073 |
+
"eval_accuracy": 0.9256110520722636,
|
| 2074 |
+
"eval_loss": 0.3105961084365845,
|
| 2075 |
+
"eval_runtime": 33.3236,
|
| 2076 |
+
"eval_samples_per_second": 28.238,
|
| 2077 |
+
"eval_steps_per_second": 3.541,
|
| 2078 |
+
"step": 3000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 9.04,
|
| 2082 |
+
"learning_rate": 1.9399399399399402e-05,
|
| 2083 |
+
"loss": 0.0942,
|
| 2084 |
+
"step": 3010
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 9.07,
|
| 2088 |
+
"learning_rate": 1.87987987987988e-05,
|
| 2089 |
+
"loss": 0.0607,
|
| 2090 |
+
"step": 3020
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 9.1,
|
| 2094 |
+
"learning_rate": 1.81981981981982e-05,
|
| 2095 |
+
"loss": 0.0353,
|
| 2096 |
+
"step": 3030
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 9.13,
|
| 2100 |
+
"learning_rate": 1.7597597597597598e-05,
|
| 2101 |
+
"loss": 0.0738,
|
| 2102 |
+
"step": 3040
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 9.16,
|
| 2106 |
+
"learning_rate": 1.6996996996996996e-05,
|
| 2107 |
+
"loss": 0.1516,
|
| 2108 |
+
"step": 3050
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 9.19,
|
| 2112 |
+
"learning_rate": 1.6396396396396396e-05,
|
| 2113 |
+
"loss": 0.0942,
|
| 2114 |
+
"step": 3060
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 9.22,
|
| 2118 |
+
"learning_rate": 1.5795795795795794e-05,
|
| 2119 |
+
"loss": 0.0873,
|
| 2120 |
+
"step": 3070
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 9.25,
|
| 2124 |
+
"learning_rate": 1.5195195195195196e-05,
|
| 2125 |
+
"loss": 0.1092,
|
| 2126 |
+
"step": 3080
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 9.28,
|
| 2130 |
+
"learning_rate": 1.4594594594594596e-05,
|
| 2131 |
+
"loss": 0.0645,
|
| 2132 |
+
"step": 3090
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 9.31,
|
| 2136 |
+
"learning_rate": 1.3993993993993995e-05,
|
| 2137 |
+
"loss": 0.2119,
|
| 2138 |
+
"step": 3100
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 9.31,
|
| 2142 |
+
"eval_accuracy": 0.9298618490967057,
|
| 2143 |
+
"eval_loss": 0.30373117327690125,
|
| 2144 |
+
"eval_runtime": 33.2692,
|
| 2145 |
+
"eval_samples_per_second": 28.284,
|
| 2146 |
+
"eval_steps_per_second": 3.547,
|
| 2147 |
+
"step": 3100
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 9.34,
|
| 2151 |
+
"learning_rate": 1.3393393393393394e-05,
|
| 2152 |
+
"loss": 0.0756,
|
| 2153 |
+
"step": 3110
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 9.37,
|
| 2157 |
+
"learning_rate": 1.2792792792792793e-05,
|
| 2158 |
+
"loss": 0.0866,
|
| 2159 |
+
"step": 3120
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 9.4,
|
| 2163 |
+
"learning_rate": 1.2192192192192192e-05,
|
| 2164 |
+
"loss": 0.043,
|
| 2165 |
+
"step": 3130
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 9.43,
|
| 2169 |
+
"learning_rate": 1.1591591591591593e-05,
|
| 2170 |
+
"loss": 0.0971,
|
| 2171 |
+
"step": 3140
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 9.46,
|
| 2175 |
+
"learning_rate": 1.0990990990990992e-05,
|
| 2176 |
+
"loss": 0.0594,
|
| 2177 |
+
"step": 3150
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 9.49,
|
| 2181 |
+
"learning_rate": 1.0390390390390391e-05,
|
| 2182 |
+
"loss": 0.0656,
|
| 2183 |
+
"step": 3160
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 9.52,
|
| 2187 |
+
"learning_rate": 9.78978978978979e-06,
|
| 2188 |
+
"loss": 0.0711,
|
| 2189 |
+
"step": 3170
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 9.55,
|
| 2193 |
+
"learning_rate": 9.18918918918919e-06,
|
| 2194 |
+
"loss": 0.1479,
|
| 2195 |
+
"step": 3180
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 9.58,
|
| 2199 |
+
"learning_rate": 8.588588588588589e-06,
|
| 2200 |
+
"loss": 0.1114,
|
| 2201 |
+
"step": 3190
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 9.61,
|
| 2205 |
+
"learning_rate": 7.987987987987988e-06,
|
| 2206 |
+
"loss": 0.1074,
|
| 2207 |
+
"step": 3200
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 9.61,
|
| 2211 |
+
"eval_accuracy": 0.9277364505844846,
|
| 2212 |
+
"eval_loss": 0.30486080050468445,
|
| 2213 |
+
"eval_runtime": 33.3497,
|
| 2214 |
+
"eval_samples_per_second": 28.216,
|
| 2215 |
+
"eval_steps_per_second": 3.538,
|
| 2216 |
+
"step": 3200
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 9.64,
|
| 2220 |
+
"learning_rate": 7.387387387387387e-06,
|
| 2221 |
+
"loss": 0.0991,
|
| 2222 |
+
"step": 3210
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 9.67,
|
| 2226 |
+
"learning_rate": 6.786786786786788e-06,
|
| 2227 |
+
"loss": 0.0901,
|
| 2228 |
+
"step": 3220
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 9.7,
|
| 2232 |
+
"learning_rate": 6.186186186186187e-06,
|
| 2233 |
+
"loss": 0.0995,
|
| 2234 |
+
"step": 3230
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 9.73,
|
| 2238 |
+
"learning_rate": 5.585585585585586e-06,
|
| 2239 |
+
"loss": 0.0859,
|
| 2240 |
+
"step": 3240
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 9.76,
|
| 2244 |
+
"learning_rate": 4.984984984984985e-06,
|
| 2245 |
+
"loss": 0.0628,
|
| 2246 |
+
"step": 3250
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 9.79,
|
| 2250 |
+
"learning_rate": 4.384384384384384e-06,
|
| 2251 |
+
"loss": 0.0797,
|
| 2252 |
+
"step": 3260
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 9.82,
|
| 2256 |
+
"learning_rate": 3.783783783783784e-06,
|
| 2257 |
+
"loss": 0.1148,
|
| 2258 |
+
"step": 3270
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 9.85,
|
| 2262 |
+
"learning_rate": 3.183183183183183e-06,
|
| 2263 |
+
"loss": 0.0777,
|
| 2264 |
+
"step": 3280
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 9.88,
|
| 2268 |
+
"learning_rate": 2.5825825825825827e-06,
|
| 2269 |
+
"loss": 0.0999,
|
| 2270 |
+
"step": 3290
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 9.91,
|
| 2274 |
+
"learning_rate": 1.981981981981982e-06,
|
| 2275 |
+
"loss": 0.1275,
|
| 2276 |
+
"step": 3300
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 9.91,
|
| 2280 |
+
"eval_accuracy": 0.9309245483528161,
|
| 2281 |
+
"eval_loss": 0.30457302927970886,
|
| 2282 |
+
"eval_runtime": 32.8441,
|
| 2283 |
+
"eval_samples_per_second": 28.65,
|
| 2284 |
+
"eval_steps_per_second": 3.593,
|
| 2285 |
+
"step": 3300
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 9.94,
|
| 2289 |
+
"learning_rate": 1.3813813813813816e-06,
|
| 2290 |
+
"loss": 0.0675,
|
| 2291 |
+
"step": 3310
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 9.97,
|
| 2295 |
+
"learning_rate": 7.807807807807808e-07,
|
| 2296 |
+
"loss": 0.059,
|
| 2297 |
+
"step": 3320
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 10.0,
|
| 2301 |
+
"learning_rate": 1.801801801801802e-07,
|
| 2302 |
+
"loss": 0.0938,
|
| 2303 |
+
"step": 3330
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 10.0,
|
| 2307 |
+
"step": 3330,
|
| 2308 |
+
"total_flos": 1.3394666639602483e+18,
|
| 2309 |
+
"train_loss": 0.2829396238287648,
|
| 2310 |
+
"train_runtime": 3129.5189,
|
| 2311 |
+
"train_samples_per_second": 17.025,
|
| 2312 |
+
"train_steps_per_second": 1.064
|
| 2313 |
+
}
|
| 2314 |
+
],
|
| 2315 |
+
"max_steps": 3330,
|
| 2316 |
+
"num_train_epochs": 10,
|
| 2317 |
+
"total_flos": 1.3394666639602483e+18,
|
| 2318 |
+
"trial_name": null,
|
| 2319 |
+
"trial_params": null
|
| 2320 |
+
}
|