End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1674976964.serv-3333.3996566.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +1285 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 83.96,
|
| 3 |
+
"eval_accuracy": 0.23073914743840437,
|
| 4 |
+
"eval_loss": 5.023878574371338,
|
| 5 |
+
"eval_runtime": 0.7662,
|
| 6 |
+
"eval_samples": 479,
|
| 7 |
+
"eval_samples_per_second": 625.177,
|
| 8 |
+
"eval_steps_per_second": 10.441,
|
| 9 |
+
"perplexity": 151.9997041360973,
|
| 10 |
+
"train_loss": 5.338385032552083,
|
| 11 |
+
"train_runtime": 55456.4482,
|
| 12 |
+
"train_samples": 228639,
|
| 13 |
+
"train_samples_per_second": 346.218,
|
| 14 |
+
"train_steps_per_second": 5.41
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 83.96,
|
| 3 |
+
"eval_accuracy": 0.23073914743840437,
|
| 4 |
+
"eval_loss": 5.023878574371338,
|
| 5 |
+
"eval_runtime": 0.7662,
|
| 6 |
+
"eval_samples": 479,
|
| 7 |
+
"eval_samples_per_second": 625.177,
|
| 8 |
+
"eval_steps_per_second": 10.441,
|
| 9 |
+
"perplexity": 151.9997041360973
|
| 10 |
+
}
|
logs/events.out.tfevents.1674976964.serv-3333.3996566.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9c97d88edc5eae72c5838b9f877ed6e594c7867039eab9cfa541220f8deba94
|
| 3 |
+
size 369
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 83.96,
|
| 3 |
+
"train_loss": 5.338385032552083,
|
| 4 |
+
"train_runtime": 55456.4482,
|
| 5 |
+
"train_samples": 228639,
|
| 6 |
+
"train_samples_per_second": 346.218,
|
| 7 |
+
"train_steps_per_second": 5.41
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 4.9971747398376465,
|
| 3 |
+
"best_model_checkpoint": "distilbert_add_pre-training-complete/checkpoint-300000",
|
| 4 |
+
"epoch": 83.9630562552477,
|
| 5 |
+
"global_step": 300000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 4.942130710236746e-05,
|
| 13 |
+
"loss": 6.295,
|
| 14 |
+
"step": 3573
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.15223537974860726,
|
| 19 |
+
"eval_loss": 6.0701375007629395,
|
| 20 |
+
"eval_runtime": 0.7526,
|
| 21 |
+
"eval_samples_per_second": 636.494,
|
| 22 |
+
"eval_steps_per_second": 10.63,
|
| 23 |
+
"step": 3573
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 4.882560853617873e-05,
|
| 28 |
+
"loss": 6.0482,
|
| 29 |
+
"step": 7146
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.15652710741946346,
|
| 34 |
+
"eval_loss": 5.953271865844727,
|
| 35 |
+
"eval_runtime": 0.74,
|
| 36 |
+
"eval_samples_per_second": 647.279,
|
| 37 |
+
"eval_steps_per_second": 10.81,
|
| 38 |
+
"step": 7146
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 4.823007669223075e-05,
|
| 43 |
+
"loss": 5.9799,
|
| 44 |
+
"step": 10719
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.15838858298685246,
|
| 49 |
+
"eval_loss": 5.900791645050049,
|
| 50 |
+
"eval_runtime": 0.7474,
|
| 51 |
+
"eval_samples_per_second": 640.85,
|
| 52 |
+
"eval_steps_per_second": 10.703,
|
| 53 |
+
"step": 10719
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"learning_rate": 4.763454484828276e-05,
|
| 58 |
+
"loss": 5.9378,
|
| 59 |
+
"step": 14292
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.1544888689508215,
|
| 64 |
+
"eval_loss": 5.899669647216797,
|
| 65 |
+
"eval_runtime": 0.741,
|
| 66 |
+
"eval_samples_per_second": 646.414,
|
| 67 |
+
"eval_steps_per_second": 10.796,
|
| 68 |
+
"step": 14292
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"learning_rate": 4.703901300433478e-05,
|
| 73 |
+
"loss": 5.9057,
|
| 74 |
+
"step": 17865
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"eval_accuracy": 0.15363002922004945,
|
| 79 |
+
"eval_loss": 5.890487194061279,
|
| 80 |
+
"eval_runtime": 0.7428,
|
| 81 |
+
"eval_samples_per_second": 644.873,
|
| 82 |
+
"eval_steps_per_second": 10.77,
|
| 83 |
+
"step": 17865
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 6.0,
|
| 87 |
+
"learning_rate": 4.644381460486829e-05,
|
| 88 |
+
"loss": 5.8811,
|
| 89 |
+
"step": 21438
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"eval_accuracy": 0.15501974055273549,
|
| 94 |
+
"eval_loss": 5.864607334136963,
|
| 95 |
+
"eval_runtime": 0.7414,
|
| 96 |
+
"eval_samples_per_second": 646.074,
|
| 97 |
+
"eval_steps_per_second": 10.79,
|
| 98 |
+
"step": 21438
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"learning_rate": 4.584828276092031e-05,
|
| 103 |
+
"loss": 5.8617,
|
| 104 |
+
"step": 25011
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"eval_accuracy": 0.15343423240607648,
|
| 109 |
+
"eval_loss": 5.832152366638184,
|
| 110 |
+
"eval_runtime": 0.7408,
|
| 111 |
+
"eval_samples_per_second": 646.572,
|
| 112 |
+
"eval_steps_per_second": 10.799,
|
| 113 |
+
"step": 25011
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"learning_rate": 4.525291763921307e-05,
|
| 118 |
+
"loss": 5.844,
|
| 119 |
+
"step": 28584
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 8.0,
|
| 123 |
+
"eval_accuracy": 0.15228028968486984,
|
| 124 |
+
"eval_loss": 5.856273651123047,
|
| 125 |
+
"eval_runtime": 0.7422,
|
| 126 |
+
"eval_samples_per_second": 645.395,
|
| 127 |
+
"eval_steps_per_second": 10.779,
|
| 128 |
+
"step": 28584
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 9.0,
|
| 132 |
+
"learning_rate": 4.4657219073024345e-05,
|
| 133 |
+
"loss": 5.8297,
|
| 134 |
+
"step": 32157
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 9.0,
|
| 138 |
+
"eval_accuracy": 0.15479184129645152,
|
| 139 |
+
"eval_loss": 5.835241794586182,
|
| 140 |
+
"eval_runtime": 0.7411,
|
| 141 |
+
"eval_samples_per_second": 646.294,
|
| 142 |
+
"eval_steps_per_second": 10.794,
|
| 143 |
+
"step": 32157
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 10.0,
|
| 147 |
+
"learning_rate": 4.4061853951317107e-05,
|
| 148 |
+
"loss": 5.8175,
|
| 149 |
+
"step": 35730
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 10.0,
|
| 153 |
+
"eval_accuracy": 0.1558288740089093,
|
| 154 |
+
"eval_loss": 5.813608646392822,
|
| 155 |
+
"eval_runtime": 0.7417,
|
| 156 |
+
"eval_samples_per_second": 645.841,
|
| 157 |
+
"eval_steps_per_second": 10.786,
|
| 158 |
+
"step": 35730
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 11.0,
|
| 162 |
+
"learning_rate": 4.3466322107369125e-05,
|
| 163 |
+
"loss": 5.8056,
|
| 164 |
+
"step": 39303
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.0,
|
| 168 |
+
"eval_accuracy": 0.15261607518586057,
|
| 169 |
+
"eval_loss": 5.81471061706543,
|
| 170 |
+
"eval_runtime": 0.7409,
|
| 171 |
+
"eval_samples_per_second": 646.53,
|
| 172 |
+
"eval_steps_per_second": 10.798,
|
| 173 |
+
"step": 39303
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 12.0,
|
| 177 |
+
"learning_rate": 4.287095698566189e-05,
|
| 178 |
+
"loss": 5.7921,
|
| 179 |
+
"step": 42876
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 12.0,
|
| 183 |
+
"eval_accuracy": 0.15484534935469516,
|
| 184 |
+
"eval_loss": 5.802037239074707,
|
| 185 |
+
"eval_runtime": 0.759,
|
| 186 |
+
"eval_samples_per_second": 631.084,
|
| 187 |
+
"eval_steps_per_second": 10.54,
|
| 188 |
+
"step": 42876
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.0,
|
| 192 |
+
"learning_rate": 4.227542514171391e-05,
|
| 193 |
+
"loss": 5.7777,
|
| 194 |
+
"step": 46449
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 13.0,
|
| 198 |
+
"eval_accuracy": 0.1545157176914121,
|
| 199 |
+
"eval_loss": 5.7890777587890625,
|
| 200 |
+
"eval_runtime": 0.7548,
|
| 201 |
+
"eval_samples_per_second": 634.635,
|
| 202 |
+
"eval_steps_per_second": 10.599,
|
| 203 |
+
"step": 46449
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 14.0,
|
| 207 |
+
"learning_rate": 4.168006002000667e-05,
|
| 208 |
+
"loss": 5.7596,
|
| 209 |
+
"step": 50022
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 14.0,
|
| 213 |
+
"eval_accuracy": 0.1587256836763462,
|
| 214 |
+
"eval_loss": 5.736998081207275,
|
| 215 |
+
"eval_runtime": 0.7569,
|
| 216 |
+
"eval_samples_per_second": 632.812,
|
| 217 |
+
"eval_steps_per_second": 10.569,
|
| 218 |
+
"step": 50022
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 15.0,
|
| 222 |
+
"learning_rate": 4.1084694898299434e-05,
|
| 223 |
+
"loss": 5.7414,
|
| 224 |
+
"step": 53595
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 15.0,
|
| 228 |
+
"eval_accuracy": 0.16035909664749615,
|
| 229 |
+
"eval_loss": 5.739556789398193,
|
| 230 |
+
"eval_runtime": 0.7394,
|
| 231 |
+
"eval_samples_per_second": 647.798,
|
| 232 |
+
"eval_steps_per_second": 10.819,
|
| 233 |
+
"step": 53595
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 16.0,
|
| 237 |
+
"learning_rate": 4.048899633211071e-05,
|
| 238 |
+
"loss": 5.7243,
|
| 239 |
+
"step": 57168
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 16.0,
|
| 243 |
+
"eval_accuracy": 0.15644779032482922,
|
| 244 |
+
"eval_loss": 5.749042510986328,
|
| 245 |
+
"eval_runtime": 0.745,
|
| 246 |
+
"eval_samples_per_second": 642.952,
|
| 247 |
+
"eval_steps_per_second": 10.738,
|
| 248 |
+
"step": 57168
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 17.0,
|
| 252 |
+
"learning_rate": 3.989346448816272e-05,
|
| 253 |
+
"loss": 5.6997,
|
| 254 |
+
"step": 60741
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 17.0,
|
| 258 |
+
"eval_accuracy": 0.15605646376164706,
|
| 259 |
+
"eval_loss": 5.713454723358154,
|
| 260 |
+
"eval_runtime": 0.7453,
|
| 261 |
+
"eval_samples_per_second": 642.723,
|
| 262 |
+
"eval_steps_per_second": 10.734,
|
| 263 |
+
"step": 60741
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 18.0,
|
| 267 |
+
"learning_rate": 3.929809936645549e-05,
|
| 268 |
+
"loss": 5.6698,
|
| 269 |
+
"step": 64314
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 18.0,
|
| 273 |
+
"eval_accuracy": 0.1619928905941432,
|
| 274 |
+
"eval_loss": 5.685813903808594,
|
| 275 |
+
"eval_runtime": 0.7411,
|
| 276 |
+
"eval_samples_per_second": 646.313,
|
| 277 |
+
"eval_steps_per_second": 10.794,
|
| 278 |
+
"step": 64314
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 19.0,
|
| 282 |
+
"learning_rate": 3.870273424474825e-05,
|
| 283 |
+
"loss": 5.6398,
|
| 284 |
+
"step": 67887
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 19.0,
|
| 288 |
+
"eval_accuracy": 0.16435543303985822,
|
| 289 |
+
"eval_loss": 5.673512935638428,
|
| 290 |
+
"eval_runtime": 0.7428,
|
| 291 |
+
"eval_samples_per_second": 644.852,
|
| 292 |
+
"eval_steps_per_second": 10.77,
|
| 293 |
+
"step": 67887
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 20.0,
|
| 297 |
+
"learning_rate": 3.810720240080027e-05,
|
| 298 |
+
"loss": 5.6135,
|
| 299 |
+
"step": 71460
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 20.0,
|
| 303 |
+
"eval_accuracy": 0.1681270846288654,
|
| 304 |
+
"eval_loss": 5.617359638214111,
|
| 305 |
+
"eval_runtime": 0.7426,
|
| 306 |
+
"eval_samples_per_second": 645.022,
|
| 307 |
+
"eval_steps_per_second": 10.773,
|
| 308 |
+
"step": 71460
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 21.0,
|
| 312 |
+
"learning_rate": 3.751217072357452e-05,
|
| 313 |
+
"loss": 5.5899,
|
| 314 |
+
"step": 75033
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 21.0,
|
| 318 |
+
"eval_accuracy": 0.1684192862736324,
|
| 319 |
+
"eval_loss": 5.619091510772705,
|
| 320 |
+
"eval_runtime": 0.7423,
|
| 321 |
+
"eval_samples_per_second": 645.301,
|
| 322 |
+
"eval_steps_per_second": 10.777,
|
| 323 |
+
"step": 75033
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 22.0,
|
| 327 |
+
"learning_rate": 3.69164721573858e-05,
|
| 328 |
+
"loss": 5.5699,
|
| 329 |
+
"step": 78606
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 22.0,
|
| 333 |
+
"eval_accuracy": 0.16689319288707669,
|
| 334 |
+
"eval_loss": 5.5976715087890625,
|
| 335 |
+
"eval_runtime": 0.7425,
|
| 336 |
+
"eval_samples_per_second": 645.154,
|
| 337 |
+
"eval_steps_per_second": 10.775,
|
| 338 |
+
"step": 78606
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 23.0,
|
| 342 |
+
"learning_rate": 3.632094031343781e-05,
|
| 343 |
+
"loss": 5.5487,
|
| 344 |
+
"step": 82179
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 23.0,
|
| 348 |
+
"eval_accuracy": 0.16692754919499106,
|
| 349 |
+
"eval_loss": 5.613892078399658,
|
| 350 |
+
"eval_runtime": 0.7425,
|
| 351 |
+
"eval_samples_per_second": 645.088,
|
| 352 |
+
"eval_steps_per_second": 10.774,
|
| 353 |
+
"step": 82179
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 24.0,
|
| 357 |
+
"learning_rate": 3.5725741913971326e-05,
|
| 358 |
+
"loss": 5.529,
|
| 359 |
+
"step": 85752
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 24.0,
|
| 363 |
+
"eval_accuracy": 0.17411228879080098,
|
| 364 |
+
"eval_loss": 5.527188301086426,
|
| 365 |
+
"eval_runtime": 0.7442,
|
| 366 |
+
"eval_samples_per_second": 643.623,
|
| 367 |
+
"eval_steps_per_second": 10.749,
|
| 368 |
+
"step": 85752
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 25.0,
|
| 372 |
+
"learning_rate": 3.5130210070023345e-05,
|
| 373 |
+
"loss": 5.512,
|
| 374 |
+
"step": 89325
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 25.0,
|
| 378 |
+
"eval_accuracy": 0.17266307533424513,
|
| 379 |
+
"eval_loss": 5.5271124839782715,
|
| 380 |
+
"eval_runtime": 0.742,
|
| 381 |
+
"eval_samples_per_second": 645.531,
|
| 382 |
+
"eval_steps_per_second": 10.781,
|
| 383 |
+
"step": 89325
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 26.0,
|
| 387 |
+
"learning_rate": 3.453467822607536e-05,
|
| 388 |
+
"loss": 5.4939,
|
| 389 |
+
"step": 92898
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 26.0,
|
| 393 |
+
"eval_accuracy": 0.1721401127408363,
|
| 394 |
+
"eval_loss": 5.518980979919434,
|
| 395 |
+
"eval_runtime": 0.7466,
|
| 396 |
+
"eval_samples_per_second": 641.587,
|
| 397 |
+
"eval_steps_per_second": 10.715,
|
| 398 |
+
"step": 92898
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 27.0,
|
| 402 |
+
"learning_rate": 3.3939313104368124e-05,
|
| 403 |
+
"loss": 5.4765,
|
| 404 |
+
"step": 96471
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 27.0,
|
| 408 |
+
"eval_accuracy": 0.17704899557659257,
|
| 409 |
+
"eval_loss": 5.482353687286377,
|
| 410 |
+
"eval_runtime": 0.7454,
|
| 411 |
+
"eval_samples_per_second": 642.613,
|
| 412 |
+
"eval_steps_per_second": 10.733,
|
| 413 |
+
"step": 96471
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 28.0,
|
| 417 |
+
"learning_rate": 3.334378126042014e-05,
|
| 418 |
+
"loss": 5.4604,
|
| 419 |
+
"step": 100044
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 28.0,
|
| 423 |
+
"eval_accuracy": 0.17465552419016742,
|
| 424 |
+
"eval_loss": 5.515853404998779,
|
| 425 |
+
"eval_runtime": 0.7444,
|
| 426 |
+
"eval_samples_per_second": 643.514,
|
| 427 |
+
"eval_steps_per_second": 10.748,
|
| 428 |
+
"step": 100044
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 29.0,
|
| 432 |
+
"learning_rate": 3.274824941647216e-05,
|
| 433 |
+
"loss": 5.4422,
|
| 434 |
+
"step": 103617
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 29.0,
|
| 438 |
+
"eval_accuracy": 0.18071012188659247,
|
| 439 |
+
"eval_loss": 5.457724571228027,
|
| 440 |
+
"eval_runtime": 0.7437,
|
| 441 |
+
"eval_samples_per_second": 644.106,
|
| 442 |
+
"eval_steps_per_second": 10.758,
|
| 443 |
+
"step": 103617
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 30.0,
|
| 447 |
+
"learning_rate": 3.215288429476492e-05,
|
| 448 |
+
"loss": 5.4243,
|
| 449 |
+
"step": 107190
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 30.0,
|
| 453 |
+
"eval_accuracy": 0.17723527446832202,
|
| 454 |
+
"eval_loss": 5.4546217918396,
|
| 455 |
+
"eval_runtime": 0.7437,
|
| 456 |
+
"eval_samples_per_second": 644.065,
|
| 457 |
+
"eval_steps_per_second": 10.757,
|
| 458 |
+
"step": 107190
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 31.0,
|
| 462 |
+
"learning_rate": 3.155735245081694e-05,
|
| 463 |
+
"loss": 5.408,
|
| 464 |
+
"step": 110763
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 31.0,
|
| 468 |
+
"eval_accuracy": 0.18372376285301534,
|
| 469 |
+
"eval_loss": 5.42967414855957,
|
| 470 |
+
"eval_runtime": 0.7402,
|
| 471 |
+
"eval_samples_per_second": 647.111,
|
| 472 |
+
"eval_steps_per_second": 10.808,
|
| 473 |
+
"step": 110763
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 32.0,
|
| 477 |
+
"learning_rate": 3.09619873291097e-05,
|
| 478 |
+
"loss": 5.3915,
|
| 479 |
+
"step": 114336
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 32.0,
|
| 483 |
+
"eval_accuracy": 0.18657804700207528,
|
| 484 |
+
"eval_loss": 5.408855438232422,
|
| 485 |
+
"eval_runtime": 0.7424,
|
| 486 |
+
"eval_samples_per_second": 645.224,
|
| 487 |
+
"eval_steps_per_second": 10.776,
|
| 488 |
+
"step": 114336
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 33.0,
|
| 492 |
+
"learning_rate": 3.0366288762920974e-05,
|
| 493 |
+
"loss": 5.3766,
|
| 494 |
+
"step": 117909
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 33.0,
|
| 498 |
+
"eval_accuracy": 0.18478903369268443,
|
| 499 |
+
"eval_loss": 5.399631023406982,
|
| 500 |
+
"eval_runtime": 0.738,
|
| 501 |
+
"eval_samples_per_second": 649.025,
|
| 502 |
+
"eval_steps_per_second": 10.84,
|
| 503 |
+
"step": 117909
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 34.0,
|
| 507 |
+
"learning_rate": 2.977092364121374e-05,
|
| 508 |
+
"loss": 5.3594,
|
| 509 |
+
"step": 121482
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 34.0,
|
| 513 |
+
"eval_accuracy": 0.1840884164346579,
|
| 514 |
+
"eval_loss": 5.397375106811523,
|
| 515 |
+
"eval_runtime": 0.7416,
|
| 516 |
+
"eval_samples_per_second": 645.897,
|
| 517 |
+
"eval_steps_per_second": 10.787,
|
| 518 |
+
"step": 121482
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 35.0,
|
| 522 |
+
"learning_rate": 2.91755585195065e-05,
|
| 523 |
+
"loss": 5.3451,
|
| 524 |
+
"step": 125055
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 35.0,
|
| 528 |
+
"eval_accuracy": 0.19081023213883255,
|
| 529 |
+
"eval_loss": 5.371816158294678,
|
| 530 |
+
"eval_runtime": 0.7407,
|
| 531 |
+
"eval_samples_per_second": 646.688,
|
| 532 |
+
"eval_steps_per_second": 10.801,
|
| 533 |
+
"step": 125055
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 36.0,
|
| 537 |
+
"learning_rate": 2.858002667555852e-05,
|
| 538 |
+
"loss": 5.3294,
|
| 539 |
+
"step": 128628
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 36.0,
|
| 543 |
+
"eval_accuracy": 0.18781625441696112,
|
| 544 |
+
"eval_loss": 5.370606422424316,
|
| 545 |
+
"eval_runtime": 0.7401,
|
| 546 |
+
"eval_samples_per_second": 647.222,
|
| 547 |
+
"eval_steps_per_second": 10.81,
|
| 548 |
+
"step": 128628
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 37.0,
|
| 552 |
+
"learning_rate": 2.7984661553851283e-05,
|
| 553 |
+
"loss": 5.3155,
|
| 554 |
+
"step": 132201
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 37.0,
|
| 558 |
+
"eval_accuracy": 0.19025888053184598,
|
| 559 |
+
"eval_loss": 5.367715835571289,
|
| 560 |
+
"eval_runtime": 0.74,
|
| 561 |
+
"eval_samples_per_second": 647.333,
|
| 562 |
+
"eval_steps_per_second": 10.811,
|
| 563 |
+
"step": 132201
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 38.0,
|
| 567 |
+
"learning_rate": 2.738929643214405e-05,
|
| 568 |
+
"loss": 5.2996,
|
| 569 |
+
"step": 135774
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 38.0,
|
| 573 |
+
"eval_accuracy": 0.1993961082531872,
|
| 574 |
+
"eval_loss": 5.296998023986816,
|
| 575 |
+
"eval_runtime": 0.741,
|
| 576 |
+
"eval_samples_per_second": 646.422,
|
| 577 |
+
"eval_steps_per_second": 10.796,
|
| 578 |
+
"step": 135774
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 39.0,
|
| 582 |
+
"learning_rate": 2.679376458819607e-05,
|
| 583 |
+
"loss": 5.287,
|
| 584 |
+
"step": 139347
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 39.0,
|
| 588 |
+
"eval_accuracy": 0.1976698373388867,
|
| 589 |
+
"eval_loss": 5.312738418579102,
|
| 590 |
+
"eval_runtime": 0.7407,
|
| 591 |
+
"eval_samples_per_second": 646.699,
|
| 592 |
+
"eval_steps_per_second": 10.801,
|
| 593 |
+
"step": 139347
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 40.0,
|
| 597 |
+
"learning_rate": 2.619856618872958e-05,
|
| 598 |
+
"loss": 5.2735,
|
| 599 |
+
"step": 142920
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 40.0,
|
| 603 |
+
"eval_accuracy": 0.1954803206793486,
|
| 604 |
+
"eval_loss": 5.314471244812012,
|
| 605 |
+
"eval_runtime": 0.7488,
|
| 606 |
+
"eval_samples_per_second": 639.694,
|
| 607 |
+
"eval_steps_per_second": 10.684,
|
| 608 |
+
"step": 142920
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 41.0,
|
| 612 |
+
"learning_rate": 2.560286762254085e-05,
|
| 613 |
+
"loss": 5.26,
|
| 614 |
+
"step": 146493
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 41.0,
|
| 618 |
+
"eval_accuracy": 0.201684222384949,
|
| 619 |
+
"eval_loss": 5.298509120941162,
|
| 620 |
+
"eval_runtime": 0.7424,
|
| 621 |
+
"eval_samples_per_second": 645.229,
|
| 622 |
+
"eval_steps_per_second": 10.776,
|
| 623 |
+
"step": 146493
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 42.0,
|
| 627 |
+
"learning_rate": 2.5007502500833613e-05,
|
| 628 |
+
"loss": 5.2487,
|
| 629 |
+
"step": 150066
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 42.0,
|
| 633 |
+
"eval_accuracy": 0.20246748544851978,
|
| 634 |
+
"eval_loss": 5.266134262084961,
|
| 635 |
+
"eval_runtime": 0.7667,
|
| 636 |
+
"eval_samples_per_second": 624.736,
|
| 637 |
+
"eval_steps_per_second": 10.434,
|
| 638 |
+
"step": 150066
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 43.0,
|
| 642 |
+
"learning_rate": 2.441197065688563e-05,
|
| 643 |
+
"loss": 5.2362,
|
| 644 |
+
"step": 153639
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 43.0,
|
| 648 |
+
"eval_accuracy": 0.2031214848143982,
|
| 649 |
+
"eval_loss": 5.2712297439575195,
|
| 650 |
+
"eval_runtime": 0.7435,
|
| 651 |
+
"eval_samples_per_second": 644.236,
|
| 652 |
+
"eval_steps_per_second": 10.76,
|
| 653 |
+
"step": 153639
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 44.0,
|
| 657 |
+
"learning_rate": 2.3816605535178393e-05,
|
| 658 |
+
"loss": 5.2248,
|
| 659 |
+
"step": 157212
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 44.0,
|
| 663 |
+
"eval_accuracy": 0.2048919322568828,
|
| 664 |
+
"eval_loss": 5.2451701164245605,
|
| 665 |
+
"eval_runtime": 0.7423,
|
| 666 |
+
"eval_samples_per_second": 645.278,
|
| 667 |
+
"eval_steps_per_second": 10.777,
|
| 668 |
+
"step": 157212
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 45.0,
|
| 672 |
+
"learning_rate": 2.3221240413471157e-05,
|
| 673 |
+
"loss": 5.2115,
|
| 674 |
+
"step": 160785
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 45.0,
|
| 678 |
+
"eval_accuracy": 0.20544290288153683,
|
| 679 |
+
"eval_loss": 5.232546806335449,
|
| 680 |
+
"eval_runtime": 0.7431,
|
| 681 |
+
"eval_samples_per_second": 644.607,
|
| 682 |
+
"eval_steps_per_second": 10.766,
|
| 683 |
+
"step": 160785
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 46.0,
|
| 687 |
+
"learning_rate": 2.2625708569523176e-05,
|
| 688 |
+
"loss": 5.1998,
|
| 689 |
+
"step": 164358
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 46.0,
|
| 693 |
+
"eval_accuracy": 0.20746922947226437,
|
| 694 |
+
"eval_loss": 5.223347187042236,
|
| 695 |
+
"eval_runtime": 0.742,
|
| 696 |
+
"eval_samples_per_second": 645.58,
|
| 697 |
+
"eval_steps_per_second": 10.782,
|
| 698 |
+
"step": 164358
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 47.0,
|
| 702 |
+
"learning_rate": 2.2030176725575194e-05,
|
| 703 |
+
"loss": 5.188,
|
| 704 |
+
"step": 167931
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 47.0,
|
| 708 |
+
"eval_accuracy": 0.21180000560836768,
|
| 709 |
+
"eval_loss": 5.199436664581299,
|
| 710 |
+
"eval_runtime": 0.748,
|
| 711 |
+
"eval_samples_per_second": 640.38,
|
| 712 |
+
"eval_steps_per_second": 10.695,
|
| 713 |
+
"step": 167931
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 48.0,
|
| 717 |
+
"learning_rate": 2.143481160386796e-05,
|
| 718 |
+
"loss": 5.1779,
|
| 719 |
+
"step": 171504
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 48.0,
|
| 723 |
+
"eval_accuracy": 0.20685218850510417,
|
| 724 |
+
"eval_loss": 5.243590354919434,
|
| 725 |
+
"eval_runtime": 0.7487,
|
| 726 |
+
"eval_samples_per_second": 639.747,
|
| 727 |
+
"eval_steps_per_second": 10.685,
|
| 728 |
+
"step": 171504
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 49.0,
|
| 732 |
+
"learning_rate": 2.083944648216072e-05,
|
| 733 |
+
"loss": 5.1664,
|
| 734 |
+
"step": 175077
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 49.0,
|
| 738 |
+
"eval_accuracy": 0.2129035902940595,
|
| 739 |
+
"eval_loss": 5.220259666442871,
|
| 740 |
+
"eval_runtime": 0.7417,
|
| 741 |
+
"eval_samples_per_second": 645.78,
|
| 742 |
+
"eval_steps_per_second": 10.785,
|
| 743 |
+
"step": 175077
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 50.0,
|
| 747 |
+
"learning_rate": 2.024391463821274e-05,
|
| 748 |
+
"loss": 5.1546,
|
| 749 |
+
"step": 178650
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 50.0,
|
| 753 |
+
"eval_accuracy": 0.21341669482933423,
|
| 754 |
+
"eval_loss": 5.181967258453369,
|
| 755 |
+
"eval_runtime": 0.74,
|
| 756 |
+
"eval_samples_per_second": 647.263,
|
| 757 |
+
"eval_steps_per_second": 10.81,
|
| 758 |
+
"step": 178650
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 51.0,
|
| 762 |
+
"learning_rate": 1.9648549516505503e-05,
|
| 763 |
+
"loss": 5.1431,
|
| 764 |
+
"step": 182223
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 51.0,
|
| 768 |
+
"eval_accuracy": 0.2122388143648584,
|
| 769 |
+
"eval_loss": 5.202933311462402,
|
| 770 |
+
"eval_runtime": 0.7441,
|
| 771 |
+
"eval_samples_per_second": 643.704,
|
| 772 |
+
"eval_steps_per_second": 10.751,
|
| 773 |
+
"step": 182223
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 52.0,
|
| 777 |
+
"learning_rate": 1.9053184394798267e-05,
|
| 778 |
+
"loss": 5.133,
|
| 779 |
+
"step": 185796
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 52.0,
|
| 783 |
+
"eval_accuracy": 0.2139890957371677,
|
| 784 |
+
"eval_loss": 5.145828723907471,
|
| 785 |
+
"eval_runtime": 0.7427,
|
| 786 |
+
"eval_samples_per_second": 644.964,
|
| 787 |
+
"eval_steps_per_second": 10.772,
|
| 788 |
+
"step": 185796
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 53.0,
|
| 792 |
+
"learning_rate": 1.8457652550850286e-05,
|
| 793 |
+
"loss": 5.1226,
|
| 794 |
+
"step": 189369
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 53.0,
|
| 798 |
+
"eval_accuracy": 0.21629691642249196,
|
| 799 |
+
"eval_loss": 5.175747394561768,
|
| 800 |
+
"eval_runtime": 0.7414,
|
| 801 |
+
"eval_samples_per_second": 646.07,
|
| 802 |
+
"eval_steps_per_second": 10.79,
|
| 803 |
+
"step": 189369
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 54.0,
|
| 807 |
+
"learning_rate": 1.7862287429143047e-05,
|
| 808 |
+
"loss": 5.1138,
|
| 809 |
+
"step": 192942
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 54.0,
|
| 813 |
+
"eval_accuracy": 0.21931465914485995,
|
| 814 |
+
"eval_loss": 5.137957572937012,
|
| 815 |
+
"eval_runtime": 0.7463,
|
| 816 |
+
"eval_samples_per_second": 641.826,
|
| 817 |
+
"eval_steps_per_second": 10.719,
|
| 818 |
+
"step": 192942
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 55.0,
|
| 822 |
+
"learning_rate": 1.726692230743581e-05,
|
| 823 |
+
"loss": 5.1046,
|
| 824 |
+
"step": 196515
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 55.0,
|
| 828 |
+
"eval_accuracy": 0.2177620690622458,
|
| 829 |
+
"eval_loss": 5.1497979164123535,
|
| 830 |
+
"eval_runtime": 0.743,
|
| 831 |
+
"eval_samples_per_second": 644.669,
|
| 832 |
+
"eval_steps_per_second": 10.767,
|
| 833 |
+
"step": 196515
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 56.0,
|
| 837 |
+
"learning_rate": 1.6671557185728576e-05,
|
| 838 |
+
"loss": 5.0984,
|
| 839 |
+
"step": 200088
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 56.0,
|
| 843 |
+
"eval_accuracy": 0.21936753338018272,
|
| 844 |
+
"eval_loss": 5.1094207763671875,
|
| 845 |
+
"eval_runtime": 0.7432,
|
| 846 |
+
"eval_samples_per_second": 644.503,
|
| 847 |
+
"eval_steps_per_second": 10.764,
|
| 848 |
+
"step": 200088
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 57.0,
|
| 852 |
+
"learning_rate": 1.6076025341780594e-05,
|
| 853 |
+
"loss": 5.0907,
|
| 854 |
+
"step": 203661
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 57.0,
|
| 858 |
+
"eval_accuracy": 0.22019682397673898,
|
| 859 |
+
"eval_loss": 5.135354995727539,
|
| 860 |
+
"eval_runtime": 0.7592,
|
| 861 |
+
"eval_samples_per_second": 630.904,
|
| 862 |
+
"eval_steps_per_second": 10.537,
|
| 863 |
+
"step": 203661
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 58.0,
|
| 867 |
+
"learning_rate": 1.548066022007336e-05,
|
| 868 |
+
"loss": 5.0812,
|
| 869 |
+
"step": 207234
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 58.0,
|
| 873 |
+
"eval_accuracy": 0.22555465405813727,
|
| 874 |
+
"eval_loss": 5.066197395324707,
|
| 875 |
+
"eval_runtime": 0.7435,
|
| 876 |
+
"eval_samples_per_second": 644.224,
|
| 877 |
+
"eval_steps_per_second": 10.759,
|
| 878 |
+
"step": 207234
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 59.0,
|
| 882 |
+
"learning_rate": 1.4885295098366123e-05,
|
| 883 |
+
"loss": 5.0748,
|
| 884 |
+
"step": 210807
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 59.0,
|
| 888 |
+
"eval_accuracy": 0.21810022855231617,
|
| 889 |
+
"eval_loss": 5.116298198699951,
|
| 890 |
+
"eval_runtime": 0.7413,
|
| 891 |
+
"eval_samples_per_second": 646.139,
|
| 892 |
+
"eval_steps_per_second": 10.791,
|
| 893 |
+
"step": 210807
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 60.0,
|
| 897 |
+
"learning_rate": 1.428976325441814e-05,
|
| 898 |
+
"loss": 5.067,
|
| 899 |
+
"step": 214380
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 60.0,
|
| 903 |
+
"eval_accuracy": 0.2199191102123357,
|
| 904 |
+
"eval_loss": 5.119345664978027,
|
| 905 |
+
"eval_runtime": 0.7438,
|
| 906 |
+
"eval_samples_per_second": 643.957,
|
| 907 |
+
"eval_steps_per_second": 10.755,
|
| 908 |
+
"step": 214380
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 61.0,
|
| 912 |
+
"learning_rate": 1.3694398132710903e-05,
|
| 913 |
+
"loss": 5.0609,
|
| 914 |
+
"step": 217953
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 61.0,
|
| 918 |
+
"eval_accuracy": 0.22237028400099942,
|
| 919 |
+
"eval_loss": 5.091867446899414,
|
| 920 |
+
"eval_runtime": 0.7487,
|
| 921 |
+
"eval_samples_per_second": 639.76,
|
| 922 |
+
"eval_steps_per_second": 10.685,
|
| 923 |
+
"step": 217953
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 62.0,
|
| 927 |
+
"learning_rate": 1.309903301100367e-05,
|
| 928 |
+
"loss": 5.0536,
|
| 929 |
+
"step": 221526
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 62.0,
|
| 933 |
+
"eval_accuracy": 0.2238659606063153,
|
| 934 |
+
"eval_loss": 5.089934349060059,
|
| 935 |
+
"eval_runtime": 0.7427,
|
| 936 |
+
"eval_samples_per_second": 644.961,
|
| 937 |
+
"eval_steps_per_second": 10.772,
|
| 938 |
+
"step": 221526
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 63.0,
|
| 942 |
+
"learning_rate": 1.2503667889296434e-05,
|
| 943 |
+
"loss": 5.0491,
|
| 944 |
+
"step": 225099
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 63.0,
|
| 948 |
+
"eval_accuracy": 0.22235195996663887,
|
| 949 |
+
"eval_loss": 5.112506866455078,
|
| 950 |
+
"eval_runtime": 0.744,
|
| 951 |
+
"eval_samples_per_second": 643.802,
|
| 952 |
+
"eval_steps_per_second": 10.752,
|
| 953 |
+
"step": 225099
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 64.0,
|
| 957 |
+
"learning_rate": 1.1907969323107703e-05,
|
| 958 |
+
"loss": 5.0433,
|
| 959 |
+
"step": 228672
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 64.0,
|
| 963 |
+
"eval_accuracy": 0.22262113416633686,
|
| 964 |
+
"eval_loss": 5.0892157554626465,
|
| 965 |
+
"eval_runtime": 0.7431,
|
| 966 |
+
"eval_samples_per_second": 644.558,
|
| 967 |
+
"eval_steps_per_second": 10.765,
|
| 968 |
+
"step": 228672
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 65.0,
|
| 972 |
+
"learning_rate": 1.1312604201400467e-05,
|
| 973 |
+
"loss": 5.0373,
|
| 974 |
+
"step": 232245
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 65.0,
|
| 978 |
+
"eval_accuracy": 0.22597519475771297,
|
| 979 |
+
"eval_loss": 5.064445972442627,
|
| 980 |
+
"eval_runtime": 0.7398,
|
| 981 |
+
"eval_samples_per_second": 647.432,
|
| 982 |
+
"eval_steps_per_second": 10.813,
|
| 983 |
+
"step": 232245
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 66.0,
|
| 987 |
+
"learning_rate": 1.0717239079693232e-05,
|
| 988 |
+
"loss": 5.032,
|
| 989 |
+
"step": 235818
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 66.0,
|
| 993 |
+
"eval_accuracy": 0.22527426278723942,
|
| 994 |
+
"eval_loss": 5.062305927276611,
|
| 995 |
+
"eval_runtime": 0.7441,
|
| 996 |
+
"eval_samples_per_second": 643.745,
|
| 997 |
+
"eval_steps_per_second": 10.751,
|
| 998 |
+
"step": 235818
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 67.0,
|
| 1002 |
+
"learning_rate": 1.0121873957985996e-05,
|
| 1003 |
+
"loss": 5.0283,
|
| 1004 |
+
"step": 239391
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 67.0,
|
| 1008 |
+
"eval_accuracy": 0.22131170544158504,
|
| 1009 |
+
"eval_loss": 5.100430011749268,
|
| 1010 |
+
"eval_runtime": 0.7454,
|
| 1011 |
+
"eval_samples_per_second": 642.6,
|
| 1012 |
+
"eval_steps_per_second": 10.732,
|
| 1013 |
+
"step": 239391
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 68.0,
|
| 1017 |
+
"learning_rate": 9.526342114038013e-06,
|
| 1018 |
+
"loss": 5.0223,
|
| 1019 |
+
"step": 242964
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 68.0,
|
| 1023 |
+
"eval_accuracy": 0.22790462549498694,
|
| 1024 |
+
"eval_loss": 5.057290077209473,
|
| 1025 |
+
"eval_runtime": 0.7453,
|
| 1026 |
+
"eval_samples_per_second": 642.666,
|
| 1027 |
+
"eval_steps_per_second": 10.733,
|
| 1028 |
+
"step": 242964
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 69.0,
|
| 1032 |
+
"learning_rate": 8.930976992330777e-06,
|
| 1033 |
+
"loss": 5.0184,
|
| 1034 |
+
"step": 246537
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 69.0,
|
| 1038 |
+
"eval_accuracy": 0.22710971646307296,
|
| 1039 |
+
"eval_loss": 5.048848628997803,
|
| 1040 |
+
"eval_runtime": 0.7418,
|
| 1041 |
+
"eval_samples_per_second": 645.766,
|
| 1042 |
+
"eval_steps_per_second": 10.785,
|
| 1043 |
+
"step": 246537
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 70.0,
|
| 1047 |
+
"learning_rate": 8.335445148382794e-06,
|
| 1048 |
+
"loss": 5.014,
|
| 1049 |
+
"step": 250110
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 70.0,
|
| 1053 |
+
"eval_accuracy": 0.22795434198746642,
|
| 1054 |
+
"eval_loss": 5.048243999481201,
|
| 1055 |
+
"eval_runtime": 0.7433,
|
| 1056 |
+
"eval_samples_per_second": 644.41,
|
| 1057 |
+
"eval_steps_per_second": 10.763,
|
| 1058 |
+
"step": 250110
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 71.0,
|
| 1062 |
+
"learning_rate": 7.740246748916306e-06,
|
| 1063 |
+
"loss": 5.0102,
|
| 1064 |
+
"step": 253683
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 71.0,
|
| 1068 |
+
"eval_accuracy": 0.22687027178481367,
|
| 1069 |
+
"eval_loss": 5.060031414031982,
|
| 1070 |
+
"eval_runtime": 0.7439,
|
| 1071 |
+
"eval_samples_per_second": 643.923,
|
| 1072 |
+
"eval_steps_per_second": 10.754,
|
| 1073 |
+
"step": 253683
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 72.0,
|
| 1077 |
+
"learning_rate": 7.144714904968323e-06,
|
| 1078 |
+
"loss": 5.0079,
|
| 1079 |
+
"step": 257256
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 72.0,
|
| 1083 |
+
"eval_accuracy": 0.2278910610607803,
|
| 1084 |
+
"eval_loss": 5.027137279510498,
|
| 1085 |
+
"eval_runtime": 0.7414,
|
| 1086 |
+
"eval_samples_per_second": 646.086,
|
| 1087 |
+
"eval_steps_per_second": 10.791,
|
| 1088 |
+
"step": 257256
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 73.0,
|
| 1092 |
+
"learning_rate": 6.549349783261087e-06,
|
| 1093 |
+
"loss": 5.0029,
|
| 1094 |
+
"step": 260829
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 73.0,
|
| 1098 |
+
"eval_accuracy": 0.22669124629908943,
|
| 1099 |
+
"eval_loss": 5.062880039215088,
|
| 1100 |
+
"eval_runtime": 0.7483,
|
| 1101 |
+
"eval_samples_per_second": 640.112,
|
| 1102 |
+
"eval_steps_per_second": 10.691,
|
| 1103 |
+
"step": 260829
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 74.0,
|
| 1107 |
+
"learning_rate": 5.9538179393131045e-06,
|
| 1108 |
+
"loss": 4.9994,
|
| 1109 |
+
"step": 264402
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 74.0,
|
| 1113 |
+
"eval_accuracy": 0.22970634211701652,
|
| 1114 |
+
"eval_loss": 5.030394554138184,
|
| 1115 |
+
"eval_runtime": 0.7474,
|
| 1116 |
+
"eval_samples_per_second": 640.862,
|
| 1117 |
+
"eval_steps_per_second": 10.703,
|
| 1118 |
+
"step": 264402
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 75.0,
|
| 1122 |
+
"learning_rate": 5.358286095365122e-06,
|
| 1123 |
+
"loss": 4.9978,
|
| 1124 |
+
"step": 267975
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 75.0,
|
| 1128 |
+
"eval_accuracy": 0.22689803559951938,
|
| 1129 |
+
"eval_loss": 5.048463821411133,
|
| 1130 |
+
"eval_runtime": 0.7472,
|
| 1131 |
+
"eval_samples_per_second": 641.032,
|
| 1132 |
+
"eval_steps_per_second": 10.706,
|
| 1133 |
+
"step": 267975
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 76.0,
|
| 1137 |
+
"learning_rate": 4.7630876958986335e-06,
|
| 1138 |
+
"loss": 4.9945,
|
| 1139 |
+
"step": 271548
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 76.0,
|
| 1143 |
+
"eval_accuracy": 0.23055979997221837,
|
| 1144 |
+
"eval_loss": 5.037987232208252,
|
| 1145 |
+
"eval_runtime": 0.7423,
|
| 1146 |
+
"eval_samples_per_second": 645.335,
|
| 1147 |
+
"eval_steps_per_second": 10.778,
|
| 1148 |
+
"step": 271548
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 77.0,
|
| 1152 |
+
"learning_rate": 4.167389129709903e-06,
|
| 1153 |
+
"loss": 4.9917,
|
| 1154 |
+
"step": 275121
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 77.0,
|
| 1158 |
+
"eval_accuracy": 0.2264717436444245,
|
| 1159 |
+
"eval_loss": 5.058966636657715,
|
| 1160 |
+
"eval_runtime": 0.7422,
|
| 1161 |
+
"eval_samples_per_second": 645.356,
|
| 1162 |
+
"eval_steps_per_second": 10.778,
|
| 1163 |
+
"step": 275121
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 78.0,
|
| 1167 |
+
"learning_rate": 3.5720240080026674e-06,
|
| 1168 |
+
"loss": 4.9913,
|
| 1169 |
+
"step": 278694
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 78.0,
|
| 1173 |
+
"eval_accuracy": 0.226176645603695,
|
| 1174 |
+
"eval_loss": 5.058542728424072,
|
| 1175 |
+
"eval_runtime": 0.7385,
|
| 1176 |
+
"eval_samples_per_second": 648.623,
|
| 1177 |
+
"eval_steps_per_second": 10.833,
|
| 1178 |
+
"step": 278694
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 79.0,
|
| 1182 |
+
"learning_rate": 2.976658886295432e-06,
|
| 1183 |
+
"loss": 4.987,
|
| 1184 |
+
"step": 282267
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 79.0,
|
| 1188 |
+
"eval_accuracy": 0.2278051787916153,
|
| 1189 |
+
"eval_loss": 5.033863544464111,
|
| 1190 |
+
"eval_runtime": 0.7435,
|
| 1191 |
+
"eval_samples_per_second": 644.245,
|
| 1192 |
+
"eval_steps_per_second": 10.76,
|
| 1193 |
+
"step": 282267
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 80.0,
|
| 1197 |
+
"learning_rate": 2.3812937645881964e-06,
|
| 1198 |
+
"loss": 4.9862,
|
| 1199 |
+
"step": 285840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 80.0,
|
| 1203 |
+
"eval_accuracy": 0.2305035650623886,
|
| 1204 |
+
"eval_loss": 5.021360397338867,
|
| 1205 |
+
"eval_runtime": 0.7486,
|
| 1206 |
+
"eval_samples_per_second": 639.881,
|
| 1207 |
+
"eval_steps_per_second": 10.687,
|
| 1208 |
+
"step": 285840
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 81.0,
|
| 1212 |
+
"learning_rate": 1.7857619206402134e-06,
|
| 1213 |
+
"loss": 4.9841,
|
| 1214 |
+
"step": 289413
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 81.0,
|
| 1218 |
+
"eval_accuracy": 0.227092194586068,
|
| 1219 |
+
"eval_loss": 5.039330005645752,
|
| 1220 |
+
"eval_runtime": 0.7471,
|
| 1221 |
+
"eval_samples_per_second": 641.165,
|
| 1222 |
+
"eval_steps_per_second": 10.708,
|
| 1223 |
+
"step": 289413
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 82.0,
|
| 1227 |
+
"learning_rate": 1.1903967989329777e-06,
|
| 1228 |
+
"loss": 4.983,
|
| 1229 |
+
"step": 292986
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 82.0,
|
| 1233 |
+
"eval_accuracy": 0.22981801867481705,
|
| 1234 |
+
"eval_loss": 5.02002477645874,
|
| 1235 |
+
"eval_runtime": 0.747,
|
| 1236 |
+
"eval_samples_per_second": 641.199,
|
| 1237 |
+
"eval_steps_per_second": 10.709,
|
| 1238 |
+
"step": 292986
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 83.0,
|
| 1242 |
+
"learning_rate": 5.95031677225742e-07,
|
| 1243 |
+
"loss": 4.9816,
|
| 1244 |
+
"step": 296559
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 83.0,
|
| 1248 |
+
"eval_accuracy": 0.22995899106791753,
|
| 1249 |
+
"eval_loss": 5.028861045837402,
|
| 1250 |
+
"eval_runtime": 0.7441,
|
| 1251 |
+
"eval_samples_per_second": 643.773,
|
| 1252 |
+
"eval_steps_per_second": 10.752,
|
| 1253 |
+
"step": 296559
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 83.96,
|
| 1257 |
+
"learning_rate": 2.1340446815605204e-08,
|
| 1258 |
+
"loss": 4.9801,
|
| 1259 |
+
"step": 300000
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 83.96,
|
| 1263 |
+
"eval_accuracy": 0.23321614400225005,
|
| 1264 |
+
"eval_loss": 4.9971747398376465,
|
| 1265 |
+
"eval_runtime": 0.7444,
|
| 1266 |
+
"eval_samples_per_second": 643.479,
|
| 1267 |
+
"eval_steps_per_second": 10.747,
|
| 1268 |
+
"step": 300000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 83.96,
|
| 1272 |
+
"step": 300000,
|
| 1273 |
+
"total_flos": 2.3423641855784387e+18,
|
| 1274 |
+
"train_loss": 5.338385032552083,
|
| 1275 |
+
"train_runtime": 55456.4482,
|
| 1276 |
+
"train_samples_per_second": 346.218,
|
| 1277 |
+
"train_steps_per_second": 5.41
|
| 1278 |
+
}
|
| 1279 |
+
],
|
| 1280 |
+
"max_steps": 300000,
|
| 1281 |
+
"num_train_epochs": 84,
|
| 1282 |
+
"total_flos": 2.3423641855784387e+18,
|
| 1283 |
+
"trial_name": null,
|
| 1284 |
+
"trial_params": null
|
| 1285 |
+
}
|