Finished training
Browse files- all_results.json +13 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652329658.r5u15n1.puma.hpc.arizona.edu.40213.0 +2 -2
- runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652349037.r5u15n1.puma.hpc.arizona.edu.40213.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +1087 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.8,
|
| 3 |
+
"eval_accuracy": 0.39707419017763845,
|
| 4 |
+
"eval_loss": 3.7512481212615967,
|
| 5 |
+
"eval_runtime": 17.386,
|
| 6 |
+
"eval_samples_per_second": 575.175,
|
| 7 |
+
"eval_steps_per_second": 18.003,
|
| 8 |
+
"perplexity": 42.574186600169504,
|
| 9 |
+
"train_loss": 3.178084816891923,
|
| 10 |
+
"train_runtime": 19361.8142,
|
| 11 |
+
"train_samples_per_second": 319.258,
|
| 12 |
+
"train_steps_per_second": 0.04
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.8,
|
| 3 |
+
"eval_accuracy": 0.39707419017763845,
|
| 4 |
+
"eval_loss": 3.7512481212615967,
|
| 5 |
+
"eval_runtime": 17.386,
|
| 6 |
+
"eval_samples_per_second": 575.175,
|
| 7 |
+
"eval_steps_per_second": 18.003,
|
| 8 |
+
"perplexity": 42.574186600169504
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438128811
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba420c5d2f8e9fdd067a7eac04a5bf1da6323ac1bc8f1d7a52ee23ec4ad12681
|
| 3 |
size 438128811
|
runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652329658.r5u15n1.puma.hpc.arizona.edu.40213.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:851e0b179c021334f968e1b26fbf3a880ca62e6d974bc45d00418290676b88d3
|
| 3 |
+
size 34729
|
runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652349037.r5u15n1.puma.hpc.arizona.edu.40213.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:753ca86c82d0c27494e3db8cffba6e3c90bf3a6faba203a33de5bfaa89581af5
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.8,
|
| 3 |
+
"train_loss": 3.178084816891923,
|
| 4 |
+
"train_runtime": 19361.8142,
|
| 5 |
+
"train_samples_per_second": 319.258,
|
| 6 |
+
"train_steps_per_second": 0.04
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1087 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.40238592824799724,
|
| 3 |
+
"best_model_checkpoint": "/groups/claytonm/enoriega/kw_pubmed/kw_pubmed_5000_0.000006/checkpoint-435",
|
| 4 |
+
"epoch": 3.795931045193353,
|
| 5 |
+
"global_step": 585,
|
| 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": 5.968831168831169e-06,
|
| 13 |
+
"loss": 4.3584,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 5.937662337662337e-06,
|
| 19 |
+
"loss": 4.0315,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 5.8987012987012994e-06,
|
| 25 |
+
"loss": 3.9357,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"eval_accuracy": 0.37917972831765934,
|
| 31 |
+
"eval_loss": 3.8932790756225586,
|
| 32 |
+
"eval_runtime": 16.4606,
|
| 33 |
+
"eval_samples_per_second": 607.512,
|
| 34 |
+
"eval_steps_per_second": 19.015,
|
| 35 |
+
"step": 15
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.13,
|
| 39 |
+
"learning_rate": 5.85974025974026e-06,
|
| 40 |
+
"loss": 3.8549,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.16,
|
| 45 |
+
"learning_rate": 5.820779220779221e-06,
|
| 46 |
+
"loss": 3.7904,
|
| 47 |
+
"step": 25
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.19,
|
| 51 |
+
"learning_rate": 5.781818181818182e-06,
|
| 52 |
+
"loss": 3.7574,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.19,
|
| 57 |
+
"eval_accuracy": 0.38153082549634276,
|
| 58 |
+
"eval_loss": 3.8384764194488525,
|
| 59 |
+
"eval_runtime": 16.5354,
|
| 60 |
+
"eval_samples_per_second": 604.762,
|
| 61 |
+
"eval_steps_per_second": 18.929,
|
| 62 |
+
"step": 30
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.23,
|
| 66 |
+
"learning_rate": 5.742857142857143e-06,
|
| 67 |
+
"loss": 3.7476,
|
| 68 |
+
"step": 35
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 5.703896103896104e-06,
|
| 73 |
+
"loss": 3.6722,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.29,
|
| 78 |
+
"learning_rate": 5.664935064935065e-06,
|
| 79 |
+
"loss": 3.6652,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.29,
|
| 84 |
+
"eval_accuracy": 0.38283699059561127,
|
| 85 |
+
"eval_loss": 3.812371015548706,
|
| 86 |
+
"eval_runtime": 16.5574,
|
| 87 |
+
"eval_samples_per_second": 603.961,
|
| 88 |
+
"eval_steps_per_second": 18.904,
|
| 89 |
+
"step": 45
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.32,
|
| 93 |
+
"learning_rate": 5.625974025974026e-06,
|
| 94 |
+
"loss": 3.6491,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.36,
|
| 99 |
+
"learning_rate": 5.587012987012987e-06,
|
| 100 |
+
"loss": 3.6096,
|
| 101 |
+
"step": 55
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.39,
|
| 105 |
+
"learning_rate": 5.548051948051948e-06,
|
| 106 |
+
"loss": 3.5893,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.39,
|
| 111 |
+
"eval_accuracy": 0.3845785440613027,
|
| 112 |
+
"eval_loss": 3.786245584487915,
|
| 113 |
+
"eval_runtime": 16.5595,
|
| 114 |
+
"eval_samples_per_second": 603.881,
|
| 115 |
+
"eval_steps_per_second": 18.901,
|
| 116 |
+
"step": 60
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.42,
|
| 120 |
+
"learning_rate": 5.50909090909091e-06,
|
| 121 |
+
"loss": 3.5818,
|
| 122 |
+
"step": 65
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.45,
|
| 126 |
+
"learning_rate": 5.47012987012987e-06,
|
| 127 |
+
"loss": 3.548,
|
| 128 |
+
"step": 70
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.49,
|
| 132 |
+
"learning_rate": 5.431168831168831e-06,
|
| 133 |
+
"loss": 3.5135,
|
| 134 |
+
"step": 75
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.49,
|
| 138 |
+
"eval_accuracy": 0.389063044235458,
|
| 139 |
+
"eval_loss": 3.7630181312561035,
|
| 140 |
+
"eval_runtime": 17.3582,
|
| 141 |
+
"eval_samples_per_second": 576.098,
|
| 142 |
+
"eval_steps_per_second": 18.032,
|
| 143 |
+
"step": 75
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.52,
|
| 147 |
+
"learning_rate": 5.3922077922077925e-06,
|
| 148 |
+
"loss": 3.51,
|
| 149 |
+
"step": 80
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.55,
|
| 153 |
+
"learning_rate": 5.353246753246754e-06,
|
| 154 |
+
"loss": 3.502,
|
| 155 |
+
"step": 85
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.58,
|
| 159 |
+
"learning_rate": 5.314285714285714e-06,
|
| 160 |
+
"loss": 3.4776,
|
| 161 |
+
"step": 90
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.58,
|
| 165 |
+
"eval_accuracy": 0.38788749564611635,
|
| 166 |
+
"eval_loss": 3.7638540267944336,
|
| 167 |
+
"eval_runtime": 17.4685,
|
| 168 |
+
"eval_samples_per_second": 572.46,
|
| 169 |
+
"eval_steps_per_second": 17.918,
|
| 170 |
+
"step": 90
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.61,
|
| 174 |
+
"learning_rate": 5.275324675324675e-06,
|
| 175 |
+
"loss": 3.455,
|
| 176 |
+
"step": 95
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.65,
|
| 180 |
+
"learning_rate": 5.2363636363636365e-06,
|
| 181 |
+
"loss": 3.4606,
|
| 182 |
+
"step": 100
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.68,
|
| 186 |
+
"learning_rate": 5.197402597402598e-06,
|
| 187 |
+
"loss": 3.4083,
|
| 188 |
+
"step": 105
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.68,
|
| 192 |
+
"eval_accuracy": 0.3912835249042146,
|
| 193 |
+
"eval_loss": 3.7579634189605713,
|
| 194 |
+
"eval_runtime": 17.4161,
|
| 195 |
+
"eval_samples_per_second": 574.181,
|
| 196 |
+
"eval_steps_per_second": 17.972,
|
| 197 |
+
"step": 105
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.71,
|
| 201 |
+
"learning_rate": 5.158441558441558e-06,
|
| 202 |
+
"loss": 3.3844,
|
| 203 |
+
"step": 110
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.74,
|
| 207 |
+
"learning_rate": 5.119480519480519e-06,
|
| 208 |
+
"loss": 3.4324,
|
| 209 |
+
"step": 115
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"learning_rate": 5.0805194805194805e-06,
|
| 214 |
+
"loss": 3.3791,
|
| 215 |
+
"step": 120
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.78,
|
| 219 |
+
"eval_accuracy": 0.38784395680947403,
|
| 220 |
+
"eval_loss": 3.7581143379211426,
|
| 221 |
+
"eval_runtime": 17.4647,
|
| 222 |
+
"eval_samples_per_second": 572.583,
|
| 223 |
+
"eval_steps_per_second": 17.922,
|
| 224 |
+
"step": 120
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.81,
|
| 228 |
+
"learning_rate": 5.041558441558442e-06,
|
| 229 |
+
"loss": 3.3814,
|
| 230 |
+
"step": 125
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.84,
|
| 234 |
+
"learning_rate": 5.002597402597402e-06,
|
| 235 |
+
"loss": 3.354,
|
| 236 |
+
"step": 130
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.87,
|
| 240 |
+
"learning_rate": 4.963636363636364e-06,
|
| 241 |
+
"loss": 3.3557,
|
| 242 |
+
"step": 135
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.87,
|
| 246 |
+
"eval_accuracy": 0.39150121908742597,
|
| 247 |
+
"eval_loss": 3.74817156791687,
|
| 248 |
+
"eval_runtime": 17.4451,
|
| 249 |
+
"eval_samples_per_second": 573.227,
|
| 250 |
+
"eval_steps_per_second": 17.942,
|
| 251 |
+
"step": 135
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.91,
|
| 255 |
+
"learning_rate": 4.924675324675325e-06,
|
| 256 |
+
"loss": 3.3157,
|
| 257 |
+
"step": 140
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.94,
|
| 261 |
+
"learning_rate": 4.885714285714286e-06,
|
| 262 |
+
"loss": 3.3465,
|
| 263 |
+
"step": 145
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.97,
|
| 267 |
+
"learning_rate": 4.846753246753247e-06,
|
| 268 |
+
"loss": 3.3077,
|
| 269 |
+
"step": 150
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.97,
|
| 273 |
+
"eval_accuracy": 0.39080459770114945,
|
| 274 |
+
"eval_loss": 3.749429702758789,
|
| 275 |
+
"eval_runtime": 17.4638,
|
| 276 |
+
"eval_samples_per_second": 572.613,
|
| 277 |
+
"eval_steps_per_second": 17.923,
|
| 278 |
+
"step": 150
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.01,
|
| 282 |
+
"learning_rate": 4.807792207792208e-06,
|
| 283 |
+
"loss": 3.6416,
|
| 284 |
+
"step": 155
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.04,
|
| 288 |
+
"learning_rate": 4.768831168831169e-06,
|
| 289 |
+
"loss": 3.2947,
|
| 290 |
+
"step": 160
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.07,
|
| 294 |
+
"learning_rate": 4.72987012987013e-06,
|
| 295 |
+
"loss": 3.2584,
|
| 296 |
+
"step": 165
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.07,
|
| 300 |
+
"eval_accuracy": 0.39372169975618254,
|
| 301 |
+
"eval_loss": 3.7410030364990234,
|
| 302 |
+
"eval_runtime": 17.4385,
|
| 303 |
+
"eval_samples_per_second": 573.445,
|
| 304 |
+
"eval_steps_per_second": 17.949,
|
| 305 |
+
"step": 165
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.1,
|
| 309 |
+
"learning_rate": 4.690909090909092e-06,
|
| 310 |
+
"loss": 3.2643,
|
| 311 |
+
"step": 170
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.14,
|
| 315 |
+
"learning_rate": 4.651948051948052e-06,
|
| 316 |
+
"loss": 3.2647,
|
| 317 |
+
"step": 175
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.17,
|
| 321 |
+
"learning_rate": 4.612987012987013e-06,
|
| 322 |
+
"loss": 3.2459,
|
| 323 |
+
"step": 180
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.17,
|
| 327 |
+
"eval_accuracy": 0.39167537443399514,
|
| 328 |
+
"eval_loss": 3.7585999965667725,
|
| 329 |
+
"eval_runtime": 17.4515,
|
| 330 |
+
"eval_samples_per_second": 573.017,
|
| 331 |
+
"eval_steps_per_second": 17.935,
|
| 332 |
+
"step": 180
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2,
|
| 336 |
+
"learning_rate": 4.574025974025974e-06,
|
| 337 |
+
"loss": 3.2303,
|
| 338 |
+
"step": 185
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.23,
|
| 342 |
+
"learning_rate": 4.535064935064936e-06,
|
| 343 |
+
"loss": 3.2218,
|
| 344 |
+
"step": 190
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.27,
|
| 348 |
+
"learning_rate": 4.496103896103896e-06,
|
| 349 |
+
"loss": 3.214,
|
| 350 |
+
"step": 195
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.27,
|
| 354 |
+
"eval_accuracy": 0.3966823406478579,
|
| 355 |
+
"eval_loss": 3.7317585945129395,
|
| 356 |
+
"eval_runtime": 17.4059,
|
| 357 |
+
"eval_samples_per_second": 574.518,
|
| 358 |
+
"eval_steps_per_second": 17.982,
|
| 359 |
+
"step": 195
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.3,
|
| 363 |
+
"learning_rate": 4.457142857142857e-06,
|
| 364 |
+
"loss": 3.1917,
|
| 365 |
+
"step": 200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.33,
|
| 369 |
+
"learning_rate": 4.418181818181818e-06,
|
| 370 |
+
"loss": 3.185,
|
| 371 |
+
"step": 205
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.36,
|
| 375 |
+
"learning_rate": 4.37922077922078e-06,
|
| 376 |
+
"loss": 3.2013,
|
| 377 |
+
"step": 210
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.36,
|
| 381 |
+
"eval_accuracy": 0.39707419017763845,
|
| 382 |
+
"eval_loss": 3.7158472537994385,
|
| 383 |
+
"eval_runtime": 17.4332,
|
| 384 |
+
"eval_samples_per_second": 573.618,
|
| 385 |
+
"eval_steps_per_second": 17.954,
|
| 386 |
+
"step": 210
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.39,
|
| 390 |
+
"learning_rate": 4.34025974025974e-06,
|
| 391 |
+
"loss": 3.1968,
|
| 392 |
+
"step": 215
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.43,
|
| 396 |
+
"learning_rate": 4.301298701298701e-06,
|
| 397 |
+
"loss": 3.1735,
|
| 398 |
+
"step": 220
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.46,
|
| 402 |
+
"learning_rate": 4.262337662337662e-06,
|
| 403 |
+
"loss": 3.1887,
|
| 404 |
+
"step": 225
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.46,
|
| 408 |
+
"eval_accuracy": 0.3923284569836294,
|
| 409 |
+
"eval_loss": 3.7491486072540283,
|
| 410 |
+
"eval_runtime": 17.4492,
|
| 411 |
+
"eval_samples_per_second": 573.091,
|
| 412 |
+
"eval_steps_per_second": 17.938,
|
| 413 |
+
"step": 225
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.49,
|
| 417 |
+
"learning_rate": 4.2233766233766236e-06,
|
| 418 |
+
"loss": 3.1663,
|
| 419 |
+
"step": 230
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.52,
|
| 423 |
+
"learning_rate": 4.184415584415584e-06,
|
| 424 |
+
"loss": 3.1689,
|
| 425 |
+
"step": 235
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.56,
|
| 429 |
+
"learning_rate": 4.145454545454546e-06,
|
| 430 |
+
"loss": 3.1359,
|
| 431 |
+
"step": 240
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.56,
|
| 435 |
+
"eval_accuracy": 0.39655172413793105,
|
| 436 |
+
"eval_loss": 3.7439537048339844,
|
| 437 |
+
"eval_runtime": 17.4433,
|
| 438 |
+
"eval_samples_per_second": 573.287,
|
| 439 |
+
"eval_steps_per_second": 17.944,
|
| 440 |
+
"step": 240
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.59,
|
| 444 |
+
"learning_rate": 4.106493506493506e-06,
|
| 445 |
+
"loss": 3.162,
|
| 446 |
+
"step": 245
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.62,
|
| 450 |
+
"learning_rate": 4.0675324675324675e-06,
|
| 451 |
+
"loss": 3.1473,
|
| 452 |
+
"step": 250
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.65,
|
| 456 |
+
"learning_rate": 4.028571428571429e-06,
|
| 457 |
+
"loss": 3.1424,
|
| 458 |
+
"step": 255
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.65,
|
| 462 |
+
"eval_accuracy": 0.3979014280738419,
|
| 463 |
+
"eval_loss": 3.724943161010742,
|
| 464 |
+
"eval_runtime": 17.4625,
|
| 465 |
+
"eval_samples_per_second": 572.655,
|
| 466 |
+
"eval_steps_per_second": 17.924,
|
| 467 |
+
"step": 255
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.69,
|
| 471 |
+
"learning_rate": 3.98961038961039e-06,
|
| 472 |
+
"loss": 3.1377,
|
| 473 |
+
"step": 260
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.72,
|
| 477 |
+
"learning_rate": 3.950649350649351e-06,
|
| 478 |
+
"loss": 3.1185,
|
| 479 |
+
"step": 265
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.75,
|
| 483 |
+
"learning_rate": 3.9116883116883115e-06,
|
| 484 |
+
"loss": 3.124,
|
| 485 |
+
"step": 270
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.75,
|
| 489 |
+
"eval_accuracy": 0.397466039707419,
|
| 490 |
+
"eval_loss": 3.734914779663086,
|
| 491 |
+
"eval_runtime": 17.4427,
|
| 492 |
+
"eval_samples_per_second": 573.305,
|
| 493 |
+
"eval_steps_per_second": 17.944,
|
| 494 |
+
"step": 270
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.78,
|
| 498 |
+
"learning_rate": 3.8727272727272735e-06,
|
| 499 |
+
"loss": 3.0861,
|
| 500 |
+
"step": 275
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.82,
|
| 504 |
+
"learning_rate": 3.833766233766234e-06,
|
| 505 |
+
"loss": 3.08,
|
| 506 |
+
"step": 280
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.85,
|
| 510 |
+
"learning_rate": 3.794805194805195e-06,
|
| 511 |
+
"loss": 3.0793,
|
| 512 |
+
"step": 285
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.85,
|
| 516 |
+
"eval_accuracy": 0.3981191222570533,
|
| 517 |
+
"eval_loss": 3.7173280715942383,
|
| 518 |
+
"eval_runtime": 17.4324,
|
| 519 |
+
"eval_samples_per_second": 573.645,
|
| 520 |
+
"eval_steps_per_second": 17.955,
|
| 521 |
+
"step": 285
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.88,
|
| 525 |
+
"learning_rate": 3.755844155844156e-06,
|
| 526 |
+
"loss": 3.0642,
|
| 527 |
+
"step": 290
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.91,
|
| 531 |
+
"learning_rate": 3.716883116883117e-06,
|
| 532 |
+
"loss": 3.0848,
|
| 533 |
+
"step": 295
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.94,
|
| 537 |
+
"learning_rate": 3.677922077922078e-06,
|
| 538 |
+
"loss": 3.0527,
|
| 539 |
+
"step": 300
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.94,
|
| 543 |
+
"eval_accuracy": 0.39973005921281785,
|
| 544 |
+
"eval_loss": 3.722606658935547,
|
| 545 |
+
"eval_runtime": 17.44,
|
| 546 |
+
"eval_samples_per_second": 573.394,
|
| 547 |
+
"eval_steps_per_second": 17.947,
|
| 548 |
+
"step": 300
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.98,
|
| 552 |
+
"learning_rate": 3.638961038961039e-06,
|
| 553 |
+
"loss": 3.062,
|
| 554 |
+
"step": 305
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.01,
|
| 558 |
+
"learning_rate": 3.6e-06,
|
| 559 |
+
"loss": 3.3985,
|
| 560 |
+
"step": 310
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.05,
|
| 564 |
+
"learning_rate": 3.5610389610389615e-06,
|
| 565 |
+
"loss": 3.049,
|
| 566 |
+
"step": 315
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.05,
|
| 570 |
+
"eval_accuracy": 0.3986415882967607,
|
| 571 |
+
"eval_loss": 3.7341573238372803,
|
| 572 |
+
"eval_runtime": 17.4676,
|
| 573 |
+
"eval_samples_per_second": 572.489,
|
| 574 |
+
"eval_steps_per_second": 17.919,
|
| 575 |
+
"step": 315
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.08,
|
| 579 |
+
"learning_rate": 3.522077922077922e-06,
|
| 580 |
+
"loss": 3.0231,
|
| 581 |
+
"step": 320
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.11,
|
| 585 |
+
"learning_rate": 3.4831168831168834e-06,
|
| 586 |
+
"loss": 3.0292,
|
| 587 |
+
"step": 325
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.14,
|
| 591 |
+
"learning_rate": 3.4441558441558442e-06,
|
| 592 |
+
"loss": 3.0422,
|
| 593 |
+
"step": 330
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.14,
|
| 597 |
+
"eval_accuracy": 0.3981191222570533,
|
| 598 |
+
"eval_loss": 3.747906446456909,
|
| 599 |
+
"eval_runtime": 17.4308,
|
| 600 |
+
"eval_samples_per_second": 573.698,
|
| 601 |
+
"eval_steps_per_second": 17.957,
|
| 602 |
+
"step": 330
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.17,
|
| 606 |
+
"learning_rate": 3.4051948051948054e-06,
|
| 607 |
+
"loss": 3.0296,
|
| 608 |
+
"step": 335
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.21,
|
| 612 |
+
"learning_rate": 3.366233766233766e-06,
|
| 613 |
+
"loss": 3.042,
|
| 614 |
+
"step": 340
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.24,
|
| 618 |
+
"learning_rate": 3.3272727272727274e-06,
|
| 619 |
+
"loss": 3.0078,
|
| 620 |
+
"step": 345
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.24,
|
| 624 |
+
"eval_accuracy": 0.39502786485545105,
|
| 625 |
+
"eval_loss": 3.7774932384490967,
|
| 626 |
+
"eval_runtime": 17.3904,
|
| 627 |
+
"eval_samples_per_second": 575.029,
|
| 628 |
+
"eval_steps_per_second": 17.998,
|
| 629 |
+
"step": 345
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.27,
|
| 633 |
+
"learning_rate": 3.288311688311688e-06,
|
| 634 |
+
"loss": 3.0348,
|
| 635 |
+
"step": 350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.3,
|
| 639 |
+
"learning_rate": 3.2493506493506494e-06,
|
| 640 |
+
"loss": 3.0249,
|
| 641 |
+
"step": 355
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.34,
|
| 645 |
+
"learning_rate": 3.21038961038961e-06,
|
| 646 |
+
"loss": 2.9674,
|
| 647 |
+
"step": 360
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.34,
|
| 651 |
+
"eval_accuracy": 0.3997735980494601,
|
| 652 |
+
"eval_loss": 3.741637945175171,
|
| 653 |
+
"eval_runtime": 17.4523,
|
| 654 |
+
"eval_samples_per_second": 572.989,
|
| 655 |
+
"eval_steps_per_second": 17.935,
|
| 656 |
+
"step": 360
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.37,
|
| 660 |
+
"learning_rate": 3.1714285714285714e-06,
|
| 661 |
+
"loss": 3.0017,
|
| 662 |
+
"step": 365
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.4,
|
| 666 |
+
"learning_rate": 3.132467532467532e-06,
|
| 667 |
+
"loss": 2.9889,
|
| 668 |
+
"step": 370
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.43,
|
| 672 |
+
"learning_rate": 3.0935064935064938e-06,
|
| 673 |
+
"loss": 2.9812,
|
| 674 |
+
"step": 375
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.43,
|
| 678 |
+
"eval_accuracy": 0.3970306513409962,
|
| 679 |
+
"eval_loss": 3.760990619659424,
|
| 680 |
+
"eval_runtime": 17.5073,
|
| 681 |
+
"eval_samples_per_second": 571.19,
|
| 682 |
+
"eval_steps_per_second": 17.878,
|
| 683 |
+
"step": 375
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.47,
|
| 687 |
+
"learning_rate": 3.054545454545454e-06,
|
| 688 |
+
"loss": 2.9882,
|
| 689 |
+
"step": 380
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.5,
|
| 693 |
+
"learning_rate": 3.0155844155844158e-06,
|
| 694 |
+
"loss": 2.9912,
|
| 695 |
+
"step": 385
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.53,
|
| 699 |
+
"learning_rate": 2.9766233766233765e-06,
|
| 700 |
+
"loss": 2.9518,
|
| 701 |
+
"step": 390
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.53,
|
| 705 |
+
"eval_accuracy": 0.3969435736677116,
|
| 706 |
+
"eval_loss": 3.7642152309417725,
|
| 707 |
+
"eval_runtime": 17.4159,
|
| 708 |
+
"eval_samples_per_second": 574.188,
|
| 709 |
+
"eval_steps_per_second": 17.972,
|
| 710 |
+
"step": 390
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.56,
|
| 714 |
+
"learning_rate": 2.9376623376623377e-06,
|
| 715 |
+
"loss": 2.9598,
|
| 716 |
+
"step": 395
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.6,
|
| 720 |
+
"learning_rate": 2.898701298701299e-06,
|
| 721 |
+
"loss": 2.9762,
|
| 722 |
+
"step": 400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.63,
|
| 726 |
+
"learning_rate": 2.8597402597402597e-06,
|
| 727 |
+
"loss": 2.9826,
|
| 728 |
+
"step": 405
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.63,
|
| 732 |
+
"eval_accuracy": 0.39946882619296414,
|
| 733 |
+
"eval_loss": 3.749140501022339,
|
| 734 |
+
"eval_runtime": 17.4742,
|
| 735 |
+
"eval_samples_per_second": 572.273,
|
| 736 |
+
"eval_steps_per_second": 17.912,
|
| 737 |
+
"step": 405
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.66,
|
| 741 |
+
"learning_rate": 2.820779220779221e-06,
|
| 742 |
+
"loss": 2.9705,
|
| 743 |
+
"step": 410
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.69,
|
| 747 |
+
"learning_rate": 2.7818181818181817e-06,
|
| 748 |
+
"loss": 2.9742,
|
| 749 |
+
"step": 415
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.72,
|
| 753 |
+
"learning_rate": 2.742857142857143e-06,
|
| 754 |
+
"loss": 2.9689,
|
| 755 |
+
"step": 420
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.72,
|
| 759 |
+
"eval_accuracy": 0.39568094740508536,
|
| 760 |
+
"eval_loss": 3.760981321334839,
|
| 761 |
+
"eval_runtime": 17.4343,
|
| 762 |
+
"eval_samples_per_second": 573.581,
|
| 763 |
+
"eval_steps_per_second": 17.953,
|
| 764 |
+
"step": 420
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.76,
|
| 768 |
+
"learning_rate": 2.7038961038961037e-06,
|
| 769 |
+
"loss": 2.9619,
|
| 770 |
+
"step": 425
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.79,
|
| 774 |
+
"learning_rate": 2.664935064935065e-06,
|
| 775 |
+
"loss": 2.9498,
|
| 776 |
+
"step": 430
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.82,
|
| 780 |
+
"learning_rate": 2.625974025974026e-06,
|
| 781 |
+
"loss": 2.9517,
|
| 782 |
+
"step": 435
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.82,
|
| 786 |
+
"eval_accuracy": 0.40238592824799724,
|
| 787 |
+
"eval_loss": 3.7294681072235107,
|
| 788 |
+
"eval_runtime": 17.4607,
|
| 789 |
+
"eval_samples_per_second": 572.714,
|
| 790 |
+
"eval_steps_per_second": 17.926,
|
| 791 |
+
"step": 435
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.85,
|
| 795 |
+
"learning_rate": 2.587012987012987e-06,
|
| 796 |
+
"loss": 2.9564,
|
| 797 |
+
"step": 440
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.89,
|
| 801 |
+
"learning_rate": 2.548051948051948e-06,
|
| 802 |
+
"loss": 2.9505,
|
| 803 |
+
"step": 445
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.92,
|
| 807 |
+
"learning_rate": 2.509090909090909e-06,
|
| 808 |
+
"loss": 2.9421,
|
| 809 |
+
"step": 450
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.92,
|
| 813 |
+
"eval_accuracy": 0.39855451062347613,
|
| 814 |
+
"eval_loss": 3.736074209213257,
|
| 815 |
+
"eval_runtime": 17.4502,
|
| 816 |
+
"eval_samples_per_second": 573.061,
|
| 817 |
+
"eval_steps_per_second": 17.937,
|
| 818 |
+
"step": 450
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.95,
|
| 822 |
+
"learning_rate": 2.4701298701298705e-06,
|
| 823 |
+
"loss": 2.9477,
|
| 824 |
+
"step": 455
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.98,
|
| 828 |
+
"learning_rate": 2.4311688311688313e-06,
|
| 829 |
+
"loss": 2.9389,
|
| 830 |
+
"step": 460
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.02,
|
| 834 |
+
"learning_rate": 2.3922077922077925e-06,
|
| 835 |
+
"loss": 3.2627,
|
| 836 |
+
"step": 465
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.02,
|
| 840 |
+
"eval_accuracy": 0.4000348310693138,
|
| 841 |
+
"eval_loss": 3.746295690536499,
|
| 842 |
+
"eval_runtime": 17.4136,
|
| 843 |
+
"eval_samples_per_second": 574.264,
|
| 844 |
+
"eval_steps_per_second": 17.974,
|
| 845 |
+
"step": 465
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.05,
|
| 849 |
+
"learning_rate": 2.3532467532467533e-06,
|
| 850 |
+
"loss": 2.9154,
|
| 851 |
+
"step": 470
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 3.08,
|
| 855 |
+
"learning_rate": 2.3142857142857145e-06,
|
| 856 |
+
"loss": 2.931,
|
| 857 |
+
"step": 475
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.12,
|
| 861 |
+
"learning_rate": 2.2753246753246757e-06,
|
| 862 |
+
"loss": 2.9189,
|
| 863 |
+
"step": 480
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.12,
|
| 867 |
+
"eval_accuracy": 0.3969435736677116,
|
| 868 |
+
"eval_loss": 3.7732067108154297,
|
| 869 |
+
"eval_runtime": 17.4617,
|
| 870 |
+
"eval_samples_per_second": 572.681,
|
| 871 |
+
"eval_steps_per_second": 17.925,
|
| 872 |
+
"step": 480
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.15,
|
| 876 |
+
"learning_rate": 2.2363636363636364e-06,
|
| 877 |
+
"loss": 2.9295,
|
| 878 |
+
"step": 485
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.18,
|
| 882 |
+
"learning_rate": 2.1974025974025976e-06,
|
| 883 |
+
"loss": 2.9133,
|
| 884 |
+
"step": 490
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.21,
|
| 888 |
+
"learning_rate": 2.1584415584415584e-06,
|
| 889 |
+
"loss": 2.9063,
|
| 890 |
+
"step": 495
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.21,
|
| 894 |
+
"eval_accuracy": 0.39990421455938696,
|
| 895 |
+
"eval_loss": 3.763644218444824,
|
| 896 |
+
"eval_runtime": 17.4503,
|
| 897 |
+
"eval_samples_per_second": 573.056,
|
| 898 |
+
"eval_steps_per_second": 17.937,
|
| 899 |
+
"step": 495
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.25,
|
| 903 |
+
"learning_rate": 2.1194805194805196e-06,
|
| 904 |
+
"loss": 2.9171,
|
| 905 |
+
"step": 500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.28,
|
| 909 |
+
"learning_rate": 2.0805194805194804e-06,
|
| 910 |
+
"loss": 2.9087,
|
| 911 |
+
"step": 505
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.31,
|
| 915 |
+
"learning_rate": 2.0415584415584416e-06,
|
| 916 |
+
"loss": 2.9181,
|
| 917 |
+
"step": 510
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.31,
|
| 921 |
+
"eval_accuracy": 0.39999129223267155,
|
| 922 |
+
"eval_loss": 3.754517078399658,
|
| 923 |
+
"eval_runtime": 17.4146,
|
| 924 |
+
"eval_samples_per_second": 574.231,
|
| 925 |
+
"eval_steps_per_second": 17.973,
|
| 926 |
+
"step": 510
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.34,
|
| 930 |
+
"learning_rate": 2.002597402597403e-06,
|
| 931 |
+
"loss": 2.8923,
|
| 932 |
+
"step": 515
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.38,
|
| 936 |
+
"learning_rate": 1.9636363636363636e-06,
|
| 937 |
+
"loss": 2.8953,
|
| 938 |
+
"step": 520
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.41,
|
| 942 |
+
"learning_rate": 1.924675324675325e-06,
|
| 943 |
+
"loss": 2.9137,
|
| 944 |
+
"step": 525
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.41,
|
| 948 |
+
"eval_accuracy": 0.4009056078021595,
|
| 949 |
+
"eval_loss": 3.7548601627349854,
|
| 950 |
+
"eval_runtime": 17.4295,
|
| 951 |
+
"eval_samples_per_second": 573.739,
|
| 952 |
+
"eval_steps_per_second": 17.958,
|
| 953 |
+
"step": 525
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.44,
|
| 957 |
+
"learning_rate": 1.8857142857142858e-06,
|
| 958 |
+
"loss": 2.8988,
|
| 959 |
+
"step": 530
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.47,
|
| 963 |
+
"learning_rate": 1.8467532467532468e-06,
|
| 964 |
+
"loss": 2.9048,
|
| 965 |
+
"step": 535
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.5,
|
| 969 |
+
"learning_rate": 1.8077922077922078e-06,
|
| 970 |
+
"loss": 2.8904,
|
| 971 |
+
"step": 540
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.5,
|
| 975 |
+
"eval_accuracy": 0.40238592824799724,
|
| 976 |
+
"eval_loss": 3.7537996768951416,
|
| 977 |
+
"eval_runtime": 17.315,
|
| 978 |
+
"eval_samples_per_second": 577.533,
|
| 979 |
+
"eval_steps_per_second": 18.077,
|
| 980 |
+
"step": 540
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.54,
|
| 984 |
+
"learning_rate": 1.7688311688311688e-06,
|
| 985 |
+
"loss": 2.9169,
|
| 986 |
+
"step": 545
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.57,
|
| 990 |
+
"learning_rate": 1.7298701298701297e-06,
|
| 991 |
+
"loss": 2.9047,
|
| 992 |
+
"step": 550
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.6,
|
| 996 |
+
"learning_rate": 1.690909090909091e-06,
|
| 997 |
+
"loss": 2.8881,
|
| 998 |
+
"step": 555
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.6,
|
| 1002 |
+
"eval_accuracy": 0.3987286659700453,
|
| 1003 |
+
"eval_loss": 3.7595129013061523,
|
| 1004 |
+
"eval_runtime": 17.237,
|
| 1005 |
+
"eval_samples_per_second": 580.149,
|
| 1006 |
+
"eval_steps_per_second": 18.159,
|
| 1007 |
+
"step": 555
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.63,
|
| 1011 |
+
"learning_rate": 1.651948051948052e-06,
|
| 1012 |
+
"loss": 2.8934,
|
| 1013 |
+
"step": 560
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.67,
|
| 1017 |
+
"learning_rate": 1.612987012987013e-06,
|
| 1018 |
+
"loss": 2.8792,
|
| 1019 |
+
"step": 565
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.7,
|
| 1023 |
+
"learning_rate": 1.574025974025974e-06,
|
| 1024 |
+
"loss": 2.8876,
|
| 1025 |
+
"step": 570
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.7,
|
| 1029 |
+
"eval_accuracy": 0.39803204458376873,
|
| 1030 |
+
"eval_loss": 3.7674362659454346,
|
| 1031 |
+
"eval_runtime": 16.7838,
|
| 1032 |
+
"eval_samples_per_second": 595.813,
|
| 1033 |
+
"eval_steps_per_second": 18.649,
|
| 1034 |
+
"step": 570
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.73,
|
| 1038 |
+
"learning_rate": 1.535064935064935e-06,
|
| 1039 |
+
"loss": 2.8712,
|
| 1040 |
+
"step": 575
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.76,
|
| 1044 |
+
"learning_rate": 1.4961038961038961e-06,
|
| 1045 |
+
"loss": 2.8557,
|
| 1046 |
+
"step": 580
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.8,
|
| 1050 |
+
"learning_rate": 1.4571428571428571e-06,
|
| 1051 |
+
"loss": 2.8805,
|
| 1052 |
+
"step": 585
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.8,
|
| 1056 |
+
"eval_accuracy": 0.4021246952281435,
|
| 1057 |
+
"eval_loss": 3.73473858833313,
|
| 1058 |
+
"eval_runtime": 17.3707,
|
| 1059 |
+
"eval_samples_per_second": 575.682,
|
| 1060 |
+
"eval_steps_per_second": 18.019,
|
| 1061 |
+
"step": 585
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 3.8,
|
| 1065 |
+
"step": 585,
|
| 1066 |
+
"total_flos": 3.8216290317512755e+17,
|
| 1067 |
+
"train_loss": 3.178084816891923,
|
| 1068 |
+
"train_runtime": 19361.8142,
|
| 1069 |
+
"train_samples_per_second": 319.258,
|
| 1070 |
+
"train_steps_per_second": 0.04
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.8,
|
| 1074 |
+
"eval_accuracy": 0.39707419017763845,
|
| 1075 |
+
"eval_loss": 3.7512481212615967,
|
| 1076 |
+
"eval_runtime": 17.386,
|
| 1077 |
+
"eval_samples_per_second": 575.175,
|
| 1078 |
+
"eval_steps_per_second": 18.003,
|
| 1079 |
+
"step": 585
|
| 1080 |
+
}
|
| 1081 |
+
],
|
| 1082 |
+
"max_steps": 770,
|
| 1083 |
+
"num_train_epochs": 5,
|
| 1084 |
+
"total_flos": 3.8216290317512755e+17,
|
| 1085 |
+
"trial_name": null,
|
| 1086 |
+
"trial_params": null
|
| 1087 |
+
}
|