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.40214.0 +2 -2
- runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652353773.r5u15n1.puma.hpc.arizona.edu.40214.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +1357 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.77,
|
| 3 |
+
"eval_accuracy": 0.4171891327063741,
|
| 4 |
+
"eval_loss": 3.979358434677124,
|
| 5 |
+
"eval_runtime": 17.2044,
|
| 6 |
+
"eval_samples_per_second": 581.246,
|
| 7 |
+
"eval_steps_per_second": 18.193,
|
| 8 |
+
"perplexity": 53.48271056576051,
|
| 9 |
+
"train_loss": 2.085782461101506,
|
| 10 |
+
"train_runtime": 24097.4857,
|
| 11 |
+
"train_samples_per_second": 256.517,
|
| 12 |
+
"train_steps_per_second": 0.032
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.77,
|
| 3 |
+
"eval_accuracy": 0.4171891327063741,
|
| 4 |
+
"eval_loss": 3.979358434677124,
|
| 5 |
+
"eval_runtime": 17.2044,
|
| 6 |
+
"eval_samples_per_second": 581.246,
|
| 7 |
+
"eval_steps_per_second": 18.193,
|
| 8 |
+
"perplexity": 53.48271056576051
|
| 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 sha256:0797d0da972ba4288f5ba9200ae0b0a2c2c047a5e7bfa8178c184d3511fbf4d3
|
| 3 |
size 438128811
|
runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652329658.r5u15n1.puma.hpc.arizona.edu.40214.0
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:d626ce569cbe0f46534aa1a1b83824caca7fda3e8307dfff7ea1801f4a3cd823
|
| 3 |
+
size 42664
|
runs/May11_21-27-26_r5u15n1.puma.hpc.arizona.edu/events.out.tfevents.1652353773.r5u15n1.puma.hpc.arizona.edu.40214.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7905ad94d38a185ea5c02e353f02e8061619271cad9ff31d8f92c9ebe2227fd
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.77,
|
| 3 |
+
"train_loss": 2.085782461101506,
|
| 4 |
+
"train_runtime": 24097.4857,
|
| 5 |
+
"train_samples_per_second": 256.517,
|
| 6 |
+
"train_steps_per_second": 0.032
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4225879484500174,
|
| 3 |
+
"best_model_checkpoint": "/groups/claytonm/enoriega/kw_pubmed/kw_pubmed_5000_0.00006/checkpoint-585",
|
| 4 |
+
"epoch": 4.770047108764301,
|
| 5 |
+
"global_step": 735,
|
| 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": 5.961038961038961e-05,
|
| 13 |
+
"loss": 4.0597,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 5.922077922077922e-05,
|
| 19 |
+
"loss": 3.63,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 5.883116883116883e-05,
|
| 25 |
+
"loss": 3.467,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"eval_accuracy": 0.3901079763148729,
|
| 31 |
+
"eval_loss": 3.7511544227600098,
|
| 32 |
+
"eval_runtime": 16.5637,
|
| 33 |
+
"eval_samples_per_second": 603.729,
|
| 34 |
+
"eval_steps_per_second": 18.897,
|
| 35 |
+
"step": 15
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.13,
|
| 39 |
+
"learning_rate": 5.844155844155844e-05,
|
| 40 |
+
"loss": 3.3347,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.16,
|
| 45 |
+
"learning_rate": 5.805194805194805e-05,
|
| 46 |
+
"loss": 3.2169,
|
| 47 |
+
"step": 25
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.19,
|
| 51 |
+
"learning_rate": 5.7662337662337664e-05,
|
| 52 |
+
"loss": 3.1359,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.19,
|
| 57 |
+
"eval_accuracy": 0.39041274817136884,
|
| 58 |
+
"eval_loss": 3.7756261825561523,
|
| 59 |
+
"eval_runtime": 16.5475,
|
| 60 |
+
"eval_samples_per_second": 604.322,
|
| 61 |
+
"eval_steps_per_second": 18.915,
|
| 62 |
+
"step": 30
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.23,
|
| 66 |
+
"learning_rate": 5.7272727272727274e-05,
|
| 67 |
+
"loss": 3.076,
|
| 68 |
+
"step": 35
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 5.6883116883116884e-05,
|
| 73 |
+
"loss": 2.9729,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.29,
|
| 78 |
+
"learning_rate": 5.6493506493506495e-05,
|
| 79 |
+
"loss": 2.931,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.29,
|
| 84 |
+
"eval_accuracy": 0.39467955416231276,
|
| 85 |
+
"eval_loss": 3.798929452896118,
|
| 86 |
+
"eval_runtime": 16.648,
|
| 87 |
+
"eval_samples_per_second": 600.672,
|
| 88 |
+
"eval_steps_per_second": 18.801,
|
| 89 |
+
"step": 45
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.32,
|
| 93 |
+
"learning_rate": 5.6103896103896105e-05,
|
| 94 |
+
"loss": 2.8682,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.36,
|
| 99 |
+
"learning_rate": 5.5714285714285715e-05,
|
| 100 |
+
"loss": 2.8255,
|
| 101 |
+
"step": 55
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.39,
|
| 105 |
+
"learning_rate": 5.5324675324675326e-05,
|
| 106 |
+
"loss": 2.7794,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.39,
|
| 111 |
+
"eval_accuracy": 0.39803204458376873,
|
| 112 |
+
"eval_loss": 3.7885875701904297,
|
| 113 |
+
"eval_runtime": 16.6293,
|
| 114 |
+
"eval_samples_per_second": 601.348,
|
| 115 |
+
"eval_steps_per_second": 18.822,
|
| 116 |
+
"step": 60
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.42,
|
| 120 |
+
"learning_rate": 5.4935064935064936e-05,
|
| 121 |
+
"loss": 2.7529,
|
| 122 |
+
"step": 65
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.45,
|
| 126 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 127 |
+
"loss": 2.699,
|
| 128 |
+
"step": 70
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.49,
|
| 132 |
+
"learning_rate": 5.4155844155844157e-05,
|
| 133 |
+
"loss": 2.6464,
|
| 134 |
+
"step": 75
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.49,
|
| 138 |
+
"eval_accuracy": 0.4050853361198189,
|
| 139 |
+
"eval_loss": 3.7896740436553955,
|
| 140 |
+
"eval_runtime": 17.133,
|
| 141 |
+
"eval_samples_per_second": 583.668,
|
| 142 |
+
"eval_steps_per_second": 18.269,
|
| 143 |
+
"step": 75
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.52,
|
| 147 |
+
"learning_rate": 5.376623376623377e-05,
|
| 148 |
+
"loss": 2.6402,
|
| 149 |
+
"step": 80
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.55,
|
| 153 |
+
"learning_rate": 5.337662337662338e-05,
|
| 154 |
+
"loss": 2.6216,
|
| 155 |
+
"step": 85
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.58,
|
| 159 |
+
"learning_rate": 5.298701298701299e-05,
|
| 160 |
+
"loss": 2.5798,
|
| 161 |
+
"step": 90
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.58,
|
| 165 |
+
"eval_accuracy": 0.40316962730755834,
|
| 166 |
+
"eval_loss": 3.832270383834839,
|
| 167 |
+
"eval_runtime": 17.2068,
|
| 168 |
+
"eval_samples_per_second": 581.165,
|
| 169 |
+
"eval_steps_per_second": 18.19,
|
| 170 |
+
"step": 90
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.61,
|
| 174 |
+
"learning_rate": 5.267532467532468e-05,
|
| 175 |
+
"loss": 2.5716,
|
| 176 |
+
"step": 95
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.65,
|
| 180 |
+
"learning_rate": 5.228571428571429e-05,
|
| 181 |
+
"loss": 2.5615,
|
| 182 |
+
"step": 100
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.68,
|
| 186 |
+
"learning_rate": 5.18961038961039e-05,
|
| 187 |
+
"loss": 2.5126,
|
| 188 |
+
"step": 105
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.68,
|
| 192 |
+
"eval_accuracy": 0.40687042842215254,
|
| 193 |
+
"eval_loss": 3.8271889686584473,
|
| 194 |
+
"eval_runtime": 17.1827,
|
| 195 |
+
"eval_samples_per_second": 581.981,
|
| 196 |
+
"eval_steps_per_second": 18.216,
|
| 197 |
+
"step": 105
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.71,
|
| 201 |
+
"learning_rate": 5.150649350649351e-05,
|
| 202 |
+
"loss": 2.4727,
|
| 203 |
+
"step": 110
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.74,
|
| 207 |
+
"learning_rate": 5.111688311688312e-05,
|
| 208 |
+
"loss": 2.5236,
|
| 209 |
+
"step": 115
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"learning_rate": 5.072727272727273e-05,
|
| 214 |
+
"loss": 2.4631,
|
| 215 |
+
"step": 120
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.78,
|
| 219 |
+
"eval_accuracy": 0.39885928247997215,
|
| 220 |
+
"eval_loss": 3.866598129272461,
|
| 221 |
+
"eval_runtime": 17.205,
|
| 222 |
+
"eval_samples_per_second": 581.228,
|
| 223 |
+
"eval_steps_per_second": 18.192,
|
| 224 |
+
"step": 120
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.81,
|
| 228 |
+
"learning_rate": 5.033766233766233e-05,
|
| 229 |
+
"loss": 2.4563,
|
| 230 |
+
"step": 125
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.84,
|
| 234 |
+
"learning_rate": 4.994805194805195e-05,
|
| 235 |
+
"loss": 2.4166,
|
| 236 |
+
"step": 130
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.87,
|
| 240 |
+
"learning_rate": 4.955844155844156e-05,
|
| 241 |
+
"loss": 2.4321,
|
| 242 |
+
"step": 135
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.87,
|
| 246 |
+
"eval_accuracy": 0.4076541274817137,
|
| 247 |
+
"eval_loss": 3.8538074493408203,
|
| 248 |
+
"eval_runtime": 17.5232,
|
| 249 |
+
"eval_samples_per_second": 570.673,
|
| 250 |
+
"eval_steps_per_second": 17.862,
|
| 251 |
+
"step": 135
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.91,
|
| 255 |
+
"learning_rate": 4.916883116883117e-05,
|
| 256 |
+
"loss": 2.3705,
|
| 257 |
+
"step": 140
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.94,
|
| 261 |
+
"learning_rate": 4.877922077922078e-05,
|
| 262 |
+
"loss": 2.3907,
|
| 263 |
+
"step": 145
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.97,
|
| 267 |
+
"learning_rate": 4.838961038961039e-05,
|
| 268 |
+
"loss": 2.357,
|
| 269 |
+
"step": 150
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.97,
|
| 273 |
+
"eval_accuracy": 0.4062173458725183,
|
| 274 |
+
"eval_loss": 3.8510184288024902,
|
| 275 |
+
"eval_runtime": 17.1923,
|
| 276 |
+
"eval_samples_per_second": 581.656,
|
| 277 |
+
"eval_steps_per_second": 18.206,
|
| 278 |
+
"step": 150
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.01,
|
| 282 |
+
"learning_rate": 4.8e-05,
|
| 283 |
+
"loss": 2.5669,
|
| 284 |
+
"step": 155
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.04,
|
| 288 |
+
"learning_rate": 4.761038961038961e-05,
|
| 289 |
+
"loss": 2.2904,
|
| 290 |
+
"step": 160
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.07,
|
| 294 |
+
"learning_rate": 4.722077922077922e-05,
|
| 295 |
+
"loss": 2.2463,
|
| 296 |
+
"step": 165
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.07,
|
| 300 |
+
"eval_accuracy": 0.4090909090909091,
|
| 301 |
+
"eval_loss": 3.870206117630005,
|
| 302 |
+
"eval_runtime": 17.2036,
|
| 303 |
+
"eval_samples_per_second": 581.273,
|
| 304 |
+
"eval_steps_per_second": 18.194,
|
| 305 |
+
"step": 165
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.1,
|
| 309 |
+
"learning_rate": 4.683116883116883e-05,
|
| 310 |
+
"loss": 2.2434,
|
| 311 |
+
"step": 170
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.14,
|
| 315 |
+
"learning_rate": 4.644155844155844e-05,
|
| 316 |
+
"loss": 2.2517,
|
| 317 |
+
"step": 175
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.17,
|
| 321 |
+
"learning_rate": 4.605194805194805e-05,
|
| 322 |
+
"loss": 2.2312,
|
| 323 |
+
"step": 180
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.17,
|
| 327 |
+
"eval_accuracy": 0.4103099965168931,
|
| 328 |
+
"eval_loss": 3.878140687942505,
|
| 329 |
+
"eval_runtime": 17.2005,
|
| 330 |
+
"eval_samples_per_second": 581.377,
|
| 331 |
+
"eval_steps_per_second": 18.197,
|
| 332 |
+
"step": 180
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2,
|
| 336 |
+
"learning_rate": 4.566233766233766e-05,
|
| 337 |
+
"loss": 2.2025,
|
| 338 |
+
"step": 185
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.23,
|
| 342 |
+
"learning_rate": 4.5272727272727274e-05,
|
| 343 |
+
"loss": 2.199,
|
| 344 |
+
"step": 190
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.27,
|
| 348 |
+
"learning_rate": 4.4883116883116884e-05,
|
| 349 |
+
"loss": 2.1948,
|
| 350 |
+
"step": 195
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.27,
|
| 354 |
+
"eval_accuracy": 0.4127917102055033,
|
| 355 |
+
"eval_loss": 3.8671493530273438,
|
| 356 |
+
"eval_runtime": 17.2222,
|
| 357 |
+
"eval_samples_per_second": 580.645,
|
| 358 |
+
"eval_steps_per_second": 18.174,
|
| 359 |
+
"step": 195
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.3,
|
| 363 |
+
"learning_rate": 4.4493506493506494e-05,
|
| 364 |
+
"loss": 2.1707,
|
| 365 |
+
"step": 200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.33,
|
| 369 |
+
"learning_rate": 4.4103896103896105e-05,
|
| 370 |
+
"loss": 2.1603,
|
| 371 |
+
"step": 205
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.36,
|
| 375 |
+
"learning_rate": 4.3714285714285715e-05,
|
| 376 |
+
"loss": 2.1735,
|
| 377 |
+
"step": 210
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.36,
|
| 381 |
+
"eval_accuracy": 0.4157088122605364,
|
| 382 |
+
"eval_loss": 3.863778829574585,
|
| 383 |
+
"eval_runtime": 17.1906,
|
| 384 |
+
"eval_samples_per_second": 581.713,
|
| 385 |
+
"eval_steps_per_second": 18.208,
|
| 386 |
+
"step": 210
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.39,
|
| 390 |
+
"learning_rate": 4.3324675324675325e-05,
|
| 391 |
+
"loss": 2.1833,
|
| 392 |
+
"step": 215
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.43,
|
| 396 |
+
"learning_rate": 4.2935064935064936e-05,
|
| 397 |
+
"loss": 2.1442,
|
| 398 |
+
"step": 220
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.46,
|
| 402 |
+
"learning_rate": 4.2545454545454546e-05,
|
| 403 |
+
"loss": 2.1541,
|
| 404 |
+
"step": 225
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.46,
|
| 408 |
+
"eval_accuracy": 0.4085249042145594,
|
| 409 |
+
"eval_loss": 3.8899924755096436,
|
| 410 |
+
"eval_runtime": 17.2073,
|
| 411 |
+
"eval_samples_per_second": 581.148,
|
| 412 |
+
"eval_steps_per_second": 18.19,
|
| 413 |
+
"step": 225
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.49,
|
| 417 |
+
"learning_rate": 4.2155844155844156e-05,
|
| 418 |
+
"loss": 2.1361,
|
| 419 |
+
"step": 230
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.52,
|
| 423 |
+
"learning_rate": 4.1766233766233767e-05,
|
| 424 |
+
"loss": 2.1254,
|
| 425 |
+
"step": 235
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.56,
|
| 429 |
+
"learning_rate": 4.137662337662338e-05,
|
| 430 |
+
"loss": 2.1117,
|
| 431 |
+
"step": 240
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.56,
|
| 435 |
+
"eval_accuracy": 0.414272030651341,
|
| 436 |
+
"eval_loss": 3.9167368412017822,
|
| 437 |
+
"eval_runtime": 17.1975,
|
| 438 |
+
"eval_samples_per_second": 581.48,
|
| 439 |
+
"eval_steps_per_second": 18.2,
|
| 440 |
+
"step": 240
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.59,
|
| 444 |
+
"learning_rate": 4.098701298701299e-05,
|
| 445 |
+
"loss": 2.1208,
|
| 446 |
+
"step": 245
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.62,
|
| 450 |
+
"learning_rate": 4.05974025974026e-05,
|
| 451 |
+
"loss": 2.0991,
|
| 452 |
+
"step": 250
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.65,
|
| 456 |
+
"learning_rate": 4.020779220779221e-05,
|
| 457 |
+
"loss": 2.1094,
|
| 458 |
+
"step": 255
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.65,
|
| 462 |
+
"eval_accuracy": 0.4169278996865204,
|
| 463 |
+
"eval_loss": 3.8918027877807617,
|
| 464 |
+
"eval_runtime": 17.2198,
|
| 465 |
+
"eval_samples_per_second": 580.727,
|
| 466 |
+
"eval_steps_per_second": 18.177,
|
| 467 |
+
"step": 255
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.69,
|
| 471 |
+
"learning_rate": 3.9818181818181825e-05,
|
| 472 |
+
"loss": 2.1038,
|
| 473 |
+
"step": 260
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.72,
|
| 477 |
+
"learning_rate": 3.942857142857143e-05,
|
| 478 |
+
"loss": 2.0806,
|
| 479 |
+
"step": 265
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.75,
|
| 483 |
+
"learning_rate": 3.9038961038961046e-05,
|
| 484 |
+
"loss": 2.0917,
|
| 485 |
+
"step": 270
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.75,
|
| 489 |
+
"eval_accuracy": 0.41300940438871475,
|
| 490 |
+
"eval_loss": 3.920091152191162,
|
| 491 |
+
"eval_runtime": 17.181,
|
| 492 |
+
"eval_samples_per_second": 582.037,
|
| 493 |
+
"eval_steps_per_second": 18.218,
|
| 494 |
+
"step": 270
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.78,
|
| 498 |
+
"learning_rate": 3.864935064935065e-05,
|
| 499 |
+
"loss": 2.0582,
|
| 500 |
+
"step": 275
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.82,
|
| 504 |
+
"learning_rate": 3.8259740259740266e-05,
|
| 505 |
+
"loss": 2.0541,
|
| 506 |
+
"step": 280
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.85,
|
| 510 |
+
"learning_rate": 3.787012987012987e-05,
|
| 511 |
+
"loss": 2.0453,
|
| 512 |
+
"step": 285
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.85,
|
| 516 |
+
"eval_accuracy": 0.41814698711250436,
|
| 517 |
+
"eval_loss": 3.8712852001190186,
|
| 518 |
+
"eval_runtime": 17.1826,
|
| 519 |
+
"eval_samples_per_second": 581.984,
|
| 520 |
+
"eval_steps_per_second": 18.216,
|
| 521 |
+
"step": 285
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.88,
|
| 525 |
+
"learning_rate": 3.748051948051949e-05,
|
| 526 |
+
"loss": 2.0351,
|
| 527 |
+
"step": 290
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.91,
|
| 531 |
+
"learning_rate": 3.709090909090909e-05,
|
| 532 |
+
"loss": 2.0527,
|
| 533 |
+
"step": 295
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.94,
|
| 537 |
+
"learning_rate": 3.670129870129871e-05,
|
| 538 |
+
"loss": 2.0247,
|
| 539 |
+
"step": 300
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.94,
|
| 543 |
+
"eval_accuracy": 0.41762452107279696,
|
| 544 |
+
"eval_loss": 3.8774173259735107,
|
| 545 |
+
"eval_runtime": 17.2528,
|
| 546 |
+
"eval_samples_per_second": 579.615,
|
| 547 |
+
"eval_steps_per_second": 18.142,
|
| 548 |
+
"step": 300
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.98,
|
| 552 |
+
"learning_rate": 3.631168831168831e-05,
|
| 553 |
+
"loss": 2.0146,
|
| 554 |
+
"step": 305
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.01,
|
| 558 |
+
"learning_rate": 3.592207792207792e-05,
|
| 559 |
+
"loss": 2.2296,
|
| 560 |
+
"step": 310
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.05,
|
| 564 |
+
"learning_rate": 3.553246753246753e-05,
|
| 565 |
+
"loss": 1.9703,
|
| 566 |
+
"step": 315
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.05,
|
| 570 |
+
"eval_accuracy": 0.4164925113200975,
|
| 571 |
+
"eval_loss": 3.891786813735962,
|
| 572 |
+
"eval_runtime": 17.1846,
|
| 573 |
+
"eval_samples_per_second": 581.915,
|
| 574 |
+
"eval_steps_per_second": 18.214,
|
| 575 |
+
"step": 315
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.08,
|
| 579 |
+
"learning_rate": 3.514285714285714e-05,
|
| 580 |
+
"loss": 1.9429,
|
| 581 |
+
"step": 320
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.11,
|
| 585 |
+
"learning_rate": 3.475324675324675e-05,
|
| 586 |
+
"loss": 1.9408,
|
| 587 |
+
"step": 325
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.14,
|
| 591 |
+
"learning_rate": 3.436363636363636e-05,
|
| 592 |
+
"loss": 1.9492,
|
| 593 |
+
"step": 330
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.14,
|
| 597 |
+
"eval_accuracy": 0.41610066179031696,
|
| 598 |
+
"eval_loss": 3.928813934326172,
|
| 599 |
+
"eval_runtime": 17.2139,
|
| 600 |
+
"eval_samples_per_second": 580.927,
|
| 601 |
+
"eval_steps_per_second": 18.183,
|
| 602 |
+
"step": 330
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.17,
|
| 606 |
+
"learning_rate": 3.397402597402597e-05,
|
| 607 |
+
"loss": 1.9459,
|
| 608 |
+
"step": 335
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.21,
|
| 612 |
+
"learning_rate": 3.3584415584415584e-05,
|
| 613 |
+
"loss": 1.9532,
|
| 614 |
+
"step": 340
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.24,
|
| 618 |
+
"learning_rate": 3.3194805194805194e-05,
|
| 619 |
+
"loss": 1.9351,
|
| 620 |
+
"step": 345
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.24,
|
| 624 |
+
"eval_accuracy": 0.4128352490421456,
|
| 625 |
+
"eval_loss": 3.947727680206299,
|
| 626 |
+
"eval_runtime": 17.2191,
|
| 627 |
+
"eval_samples_per_second": 580.75,
|
| 628 |
+
"eval_steps_per_second": 18.177,
|
| 629 |
+
"step": 345
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.27,
|
| 633 |
+
"learning_rate": 3.2805194805194804e-05,
|
| 634 |
+
"loss": 1.9483,
|
| 635 |
+
"step": 350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.3,
|
| 639 |
+
"learning_rate": 3.2415584415584415e-05,
|
| 640 |
+
"loss": 1.9433,
|
| 641 |
+
"step": 355
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.34,
|
| 645 |
+
"learning_rate": 3.2025974025974025e-05,
|
| 646 |
+
"loss": 1.9001,
|
| 647 |
+
"step": 360
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.34,
|
| 651 |
+
"eval_accuracy": 0.4186259143155695,
|
| 652 |
+
"eval_loss": 3.9299826622009277,
|
| 653 |
+
"eval_runtime": 17.1998,
|
| 654 |
+
"eval_samples_per_second": 581.401,
|
| 655 |
+
"eval_steps_per_second": 18.198,
|
| 656 |
+
"step": 360
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.37,
|
| 660 |
+
"learning_rate": 3.1636363636363635e-05,
|
| 661 |
+
"loss": 1.9127,
|
| 662 |
+
"step": 365
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.4,
|
| 666 |
+
"learning_rate": 3.1246753246753246e-05,
|
| 667 |
+
"loss": 1.9051,
|
| 668 |
+
"step": 370
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.43,
|
| 672 |
+
"learning_rate": 3.0857142857142856e-05,
|
| 673 |
+
"loss": 1.9082,
|
| 674 |
+
"step": 375
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.43,
|
| 678 |
+
"eval_accuracy": 0.4161442006269592,
|
| 679 |
+
"eval_loss": 3.9622690677642822,
|
| 680 |
+
"eval_runtime": 17.2078,
|
| 681 |
+
"eval_samples_per_second": 581.133,
|
| 682 |
+
"eval_steps_per_second": 18.189,
|
| 683 |
+
"step": 375
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.47,
|
| 687 |
+
"learning_rate": 3.046753246753247e-05,
|
| 688 |
+
"loss": 1.8929,
|
| 689 |
+
"step": 380
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.5,
|
| 693 |
+
"learning_rate": 3.0077922077922077e-05,
|
| 694 |
+
"loss": 1.912,
|
| 695 |
+
"step": 385
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.53,
|
| 699 |
+
"learning_rate": 2.968831168831169e-05,
|
| 700 |
+
"loss": 1.8804,
|
| 701 |
+
"step": 390
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.53,
|
| 705 |
+
"eval_accuracy": 0.4174503657262278,
|
| 706 |
+
"eval_loss": 3.9447922706604004,
|
| 707 |
+
"eval_runtime": 17.219,
|
| 708 |
+
"eval_samples_per_second": 580.753,
|
| 709 |
+
"eval_steps_per_second": 18.178,
|
| 710 |
+
"step": 390
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.56,
|
| 714 |
+
"learning_rate": 2.92987012987013e-05,
|
| 715 |
+
"loss": 1.8821,
|
| 716 |
+
"step": 395
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.6,
|
| 720 |
+
"learning_rate": 2.890909090909091e-05,
|
| 721 |
+
"loss": 1.8962,
|
| 722 |
+
"step": 400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.63,
|
| 726 |
+
"learning_rate": 2.851948051948052e-05,
|
| 727 |
+
"loss": 1.8962,
|
| 728 |
+
"step": 405
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.63,
|
| 732 |
+
"eval_accuracy": 0.4183646812957158,
|
| 733 |
+
"eval_loss": 3.939225673675537,
|
| 734 |
+
"eval_runtime": 17.2072,
|
| 735 |
+
"eval_samples_per_second": 581.153,
|
| 736 |
+
"eval_steps_per_second": 18.19,
|
| 737 |
+
"step": 405
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.66,
|
| 741 |
+
"learning_rate": 2.812987012987013e-05,
|
| 742 |
+
"loss": 1.8903,
|
| 743 |
+
"step": 410
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.69,
|
| 747 |
+
"learning_rate": 2.774025974025974e-05,
|
| 748 |
+
"loss": 1.8881,
|
| 749 |
+
"step": 415
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.72,
|
| 753 |
+
"learning_rate": 2.735064935064935e-05,
|
| 754 |
+
"loss": 1.884,
|
| 755 |
+
"step": 420
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.72,
|
| 759 |
+
"eval_accuracy": 0.4125740160222919,
|
| 760 |
+
"eval_loss": 3.95487380027771,
|
| 761 |
+
"eval_runtime": 17.2137,
|
| 762 |
+
"eval_samples_per_second": 580.934,
|
| 763 |
+
"eval_steps_per_second": 18.183,
|
| 764 |
+
"step": 420
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.76,
|
| 768 |
+
"learning_rate": 2.696103896103896e-05,
|
| 769 |
+
"loss": 1.8694,
|
| 770 |
+
"step": 425
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.79,
|
| 774 |
+
"learning_rate": 2.657142857142857e-05,
|
| 775 |
+
"loss": 1.872,
|
| 776 |
+
"step": 430
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.82,
|
| 780 |
+
"learning_rate": 2.618181818181818e-05,
|
| 781 |
+
"loss": 1.8689,
|
| 782 |
+
"step": 435
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.82,
|
| 786 |
+
"eval_accuracy": 0.4190613026819923,
|
| 787 |
+
"eval_loss": 3.909341812133789,
|
| 788 |
+
"eval_runtime": 17.2189,
|
| 789 |
+
"eval_samples_per_second": 580.758,
|
| 790 |
+
"eval_steps_per_second": 18.178,
|
| 791 |
+
"step": 435
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.85,
|
| 795 |
+
"learning_rate": 2.579220779220779e-05,
|
| 796 |
+
"loss": 1.877,
|
| 797 |
+
"step": 440
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.89,
|
| 801 |
+
"learning_rate": 2.54025974025974e-05,
|
| 802 |
+
"loss": 1.8685,
|
| 803 |
+
"step": 445
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.92,
|
| 807 |
+
"learning_rate": 2.501298701298701e-05,
|
| 808 |
+
"loss": 1.8522,
|
| 809 |
+
"step": 450
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.92,
|
| 813 |
+
"eval_accuracy": 0.4203239289446186,
|
| 814 |
+
"eval_loss": 3.9448978900909424,
|
| 815 |
+
"eval_runtime": 17.2358,
|
| 816 |
+
"eval_samples_per_second": 580.188,
|
| 817 |
+
"eval_steps_per_second": 18.16,
|
| 818 |
+
"step": 450
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.95,
|
| 822 |
+
"learning_rate": 2.4623376623376625e-05,
|
| 823 |
+
"loss": 1.8654,
|
| 824 |
+
"step": 455
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.98,
|
| 828 |
+
"learning_rate": 2.4233766233766235e-05,
|
| 829 |
+
"loss": 1.8605,
|
| 830 |
+
"step": 460
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.02,
|
| 834 |
+
"learning_rate": 2.3844155844155845e-05,
|
| 835 |
+
"loss": 2.037,
|
| 836 |
+
"step": 465
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.02,
|
| 840 |
+
"eval_accuracy": 0.41705851619644724,
|
| 841 |
+
"eval_loss": 3.981081008911133,
|
| 842 |
+
"eval_runtime": 17.206,
|
| 843 |
+
"eval_samples_per_second": 581.194,
|
| 844 |
+
"eval_steps_per_second": 18.191,
|
| 845 |
+
"step": 465
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.05,
|
| 849 |
+
"learning_rate": 2.3454545454545456e-05,
|
| 850 |
+
"loss": 1.8046,
|
| 851 |
+
"step": 470
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 3.08,
|
| 855 |
+
"learning_rate": 2.3064935064935066e-05,
|
| 856 |
+
"loss": 1.8011,
|
| 857 |
+
"step": 475
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.12,
|
| 861 |
+
"learning_rate": 2.2675324675324676e-05,
|
| 862 |
+
"loss": 1.8038,
|
| 863 |
+
"step": 480
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.12,
|
| 867 |
+
"eval_accuracy": 0.4150992685475444,
|
| 868 |
+
"eval_loss": 3.9613595008850098,
|
| 869 |
+
"eval_runtime": 17.1973,
|
| 870 |
+
"eval_samples_per_second": 581.488,
|
| 871 |
+
"eval_steps_per_second": 18.201,
|
| 872 |
+
"step": 480
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.15,
|
| 876 |
+
"learning_rate": 2.2285714285714287e-05,
|
| 877 |
+
"loss": 1.8073,
|
| 878 |
+
"step": 485
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.18,
|
| 882 |
+
"learning_rate": 2.1896103896103897e-05,
|
| 883 |
+
"loss": 1.783,
|
| 884 |
+
"step": 490
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.21,
|
| 888 |
+
"learning_rate": 2.1506493506493507e-05,
|
| 889 |
+
"loss": 1.805,
|
| 890 |
+
"step": 495
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.21,
|
| 894 |
+
"eval_accuracy": 0.41819052594914663,
|
| 895 |
+
"eval_loss": 3.9464197158813477,
|
| 896 |
+
"eval_runtime": 17.2204,
|
| 897 |
+
"eval_samples_per_second": 580.705,
|
| 898 |
+
"eval_steps_per_second": 18.176,
|
| 899 |
+
"step": 495
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.25,
|
| 903 |
+
"learning_rate": 2.1116883116883118e-05,
|
| 904 |
+
"loss": 1.7972,
|
| 905 |
+
"step": 500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.28,
|
| 909 |
+
"learning_rate": 2.0727272727272728e-05,
|
| 910 |
+
"loss": 1.7782,
|
| 911 |
+
"step": 505
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.31,
|
| 915 |
+
"learning_rate": 2.033766233766234e-05,
|
| 916 |
+
"loss": 1.8135,
|
| 917 |
+
"step": 510
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.31,
|
| 921 |
+
"eval_accuracy": 0.41592650644374785,
|
| 922 |
+
"eval_loss": 3.9678966999053955,
|
| 923 |
+
"eval_runtime": 17.1877,
|
| 924 |
+
"eval_samples_per_second": 581.811,
|
| 925 |
+
"eval_steps_per_second": 18.211,
|
| 926 |
+
"step": 510
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.34,
|
| 930 |
+
"learning_rate": 1.994805194805195e-05,
|
| 931 |
+
"loss": 1.7835,
|
| 932 |
+
"step": 515
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.38,
|
| 936 |
+
"learning_rate": 1.955844155844156e-05,
|
| 937 |
+
"loss": 1.782,
|
| 938 |
+
"step": 520
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.41,
|
| 942 |
+
"learning_rate": 1.916883116883117e-05,
|
| 943 |
+
"loss": 1.7927,
|
| 944 |
+
"step": 525
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.41,
|
| 948 |
+
"eval_accuracy": 0.419932079414838,
|
| 949 |
+
"eval_loss": 3.9554903507232666,
|
| 950 |
+
"eval_runtime": 17.1692,
|
| 951 |
+
"eval_samples_per_second": 582.437,
|
| 952 |
+
"eval_steps_per_second": 18.23,
|
| 953 |
+
"step": 525
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.44,
|
| 957 |
+
"learning_rate": 1.877922077922078e-05,
|
| 958 |
+
"loss": 1.7979,
|
| 959 |
+
"step": 530
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.47,
|
| 963 |
+
"learning_rate": 1.838961038961039e-05,
|
| 964 |
+
"loss": 1.7894,
|
| 965 |
+
"step": 535
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.5,
|
| 969 |
+
"learning_rate": 1.8e-05,
|
| 970 |
+
"loss": 1.7723,
|
| 971 |
+
"step": 540
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.5,
|
| 975 |
+
"eval_accuracy": 0.41936607453848834,
|
| 976 |
+
"eval_loss": 3.970630645751953,
|
| 977 |
+
"eval_runtime": 17.1943,
|
| 978 |
+
"eval_samples_per_second": 581.588,
|
| 979 |
+
"eval_steps_per_second": 18.204,
|
| 980 |
+
"step": 540
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.54,
|
| 984 |
+
"learning_rate": 1.761038961038961e-05,
|
| 985 |
+
"loss": 1.797,
|
| 986 |
+
"step": 545
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.57,
|
| 990 |
+
"learning_rate": 1.722077922077922e-05,
|
| 991 |
+
"loss": 1.7836,
|
| 992 |
+
"step": 550
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.6,
|
| 996 |
+
"learning_rate": 1.683116883116883e-05,
|
| 997 |
+
"loss": 1.7893,
|
| 998 |
+
"step": 555
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.6,
|
| 1002 |
+
"eval_accuracy": 0.4174068268895855,
|
| 1003 |
+
"eval_loss": 3.984471321105957,
|
| 1004 |
+
"eval_runtime": 17.1471,
|
| 1005 |
+
"eval_samples_per_second": 583.19,
|
| 1006 |
+
"eval_steps_per_second": 18.254,
|
| 1007 |
+
"step": 555
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.63,
|
| 1011 |
+
"learning_rate": 1.6441558441558442e-05,
|
| 1012 |
+
"loss": 1.7891,
|
| 1013 |
+
"step": 560
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.67,
|
| 1017 |
+
"learning_rate": 1.6051948051948052e-05,
|
| 1018 |
+
"loss": 1.7564,
|
| 1019 |
+
"step": 565
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.7,
|
| 1023 |
+
"learning_rate": 1.5662337662337662e-05,
|
| 1024 |
+
"loss": 1.7725,
|
| 1025 |
+
"step": 570
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.7,
|
| 1029 |
+
"eval_accuracy": 0.41762452107279696,
|
| 1030 |
+
"eval_loss": 3.9673519134521484,
|
| 1031 |
+
"eval_runtime": 16.8716,
|
| 1032 |
+
"eval_samples_per_second": 592.713,
|
| 1033 |
+
"eval_steps_per_second": 18.552,
|
| 1034 |
+
"step": 570
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.73,
|
| 1038 |
+
"learning_rate": 1.5272727272727273e-05,
|
| 1039 |
+
"loss": 1.7631,
|
| 1040 |
+
"step": 575
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.76,
|
| 1044 |
+
"learning_rate": 1.4883116883116883e-05,
|
| 1045 |
+
"loss": 1.7441,
|
| 1046 |
+
"step": 580
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.8,
|
| 1050 |
+
"learning_rate": 1.4493506493506493e-05,
|
| 1051 |
+
"loss": 1.7721,
|
| 1052 |
+
"step": 585
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.8,
|
| 1056 |
+
"eval_accuracy": 0.4225879484500174,
|
| 1057 |
+
"eval_loss": 3.9382729530334473,
|
| 1058 |
+
"eval_runtime": 17.13,
|
| 1059 |
+
"eval_samples_per_second": 583.773,
|
| 1060 |
+
"eval_steps_per_second": 18.272,
|
| 1061 |
+
"step": 585
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 3.83,
|
| 1065 |
+
"learning_rate": 1.4103896103896104e-05,
|
| 1066 |
+
"loss": 1.7317,
|
| 1067 |
+
"step": 590
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 3.86,
|
| 1071 |
+
"learning_rate": 1.3714285714285714e-05,
|
| 1072 |
+
"loss": 1.7738,
|
| 1073 |
+
"step": 595
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.89,
|
| 1077 |
+
"learning_rate": 1.3324675324675324e-05,
|
| 1078 |
+
"loss": 1.7533,
|
| 1079 |
+
"step": 600
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 3.89,
|
| 1083 |
+
"eval_accuracy": 0.4196708463949843,
|
| 1084 |
+
"eval_loss": 3.96612811088562,
|
| 1085 |
+
"eval_runtime": 17.1432,
|
| 1086 |
+
"eval_samples_per_second": 583.32,
|
| 1087 |
+
"eval_steps_per_second": 18.258,
|
| 1088 |
+
"step": 600
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.93,
|
| 1092 |
+
"learning_rate": 1.2935064935064935e-05,
|
| 1093 |
+
"loss": 1.7658,
|
| 1094 |
+
"step": 605
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.96,
|
| 1098 |
+
"learning_rate": 1.2545454545454545e-05,
|
| 1099 |
+
"loss": 1.7635,
|
| 1100 |
+
"step": 610
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.99,
|
| 1104 |
+
"learning_rate": 1.2155844155844157e-05,
|
| 1105 |
+
"loss": 1.7437,
|
| 1106 |
+
"step": 615
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.99,
|
| 1110 |
+
"eval_accuracy": 0.41910484151863464,
|
| 1111 |
+
"eval_loss": 3.972932815551758,
|
| 1112 |
+
"eval_runtime": 17.2356,
|
| 1113 |
+
"eval_samples_per_second": 580.195,
|
| 1114 |
+
"eval_steps_per_second": 18.16,
|
| 1115 |
+
"step": 615
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 4.03,
|
| 1119 |
+
"learning_rate": 1.1766233766233768e-05,
|
| 1120 |
+
"loss": 1.9054,
|
| 1121 |
+
"step": 620
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 4.06,
|
| 1125 |
+
"learning_rate": 1.1376623376623378e-05,
|
| 1126 |
+
"loss": 1.7217,
|
| 1127 |
+
"step": 625
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 4.09,
|
| 1131 |
+
"learning_rate": 1.0987012987012988e-05,
|
| 1132 |
+
"loss": 1.7418,
|
| 1133 |
+
"step": 630
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 4.09,
|
| 1137 |
+
"eval_accuracy": 0.4188000696621386,
|
| 1138 |
+
"eval_loss": 4.000043869018555,
|
| 1139 |
+
"eval_runtime": 17.2412,
|
| 1140 |
+
"eval_samples_per_second": 580.005,
|
| 1141 |
+
"eval_steps_per_second": 18.154,
|
| 1142 |
+
"step": 630
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.12,
|
| 1146 |
+
"learning_rate": 1.0597402597402599e-05,
|
| 1147 |
+
"loss": 1.6958,
|
| 1148 |
+
"step": 635
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.16,
|
| 1152 |
+
"learning_rate": 1.0207792207792209e-05,
|
| 1153 |
+
"loss": 1.7156,
|
| 1154 |
+
"step": 640
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 4.19,
|
| 1158 |
+
"learning_rate": 9.81818181818182e-06,
|
| 1159 |
+
"loss": 1.7237,
|
| 1160 |
+
"step": 645
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 4.19,
|
| 1164 |
+
"eval_accuracy": 0.42106408916753746,
|
| 1165 |
+
"eval_loss": 3.971540927886963,
|
| 1166 |
+
"eval_runtime": 17.1943,
|
| 1167 |
+
"eval_samples_per_second": 581.589,
|
| 1168 |
+
"eval_steps_per_second": 18.204,
|
| 1169 |
+
"step": 645
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 4.22,
|
| 1173 |
+
"learning_rate": 9.428571428571428e-06,
|
| 1174 |
+
"loss": 1.7111,
|
| 1175 |
+
"step": 650
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 4.25,
|
| 1179 |
+
"learning_rate": 9.038961038961038e-06,
|
| 1180 |
+
"loss": 1.7228,
|
| 1181 |
+
"step": 655
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 4.28,
|
| 1185 |
+
"learning_rate": 8.649350649350649e-06,
|
| 1186 |
+
"loss": 1.7029,
|
| 1187 |
+
"step": 660
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 4.28,
|
| 1191 |
+
"eval_accuracy": 0.41919191919191917,
|
| 1192 |
+
"eval_loss": 4.000442981719971,
|
| 1193 |
+
"eval_runtime": 17.2363,
|
| 1194 |
+
"eval_samples_per_second": 580.172,
|
| 1195 |
+
"eval_steps_per_second": 18.159,
|
| 1196 |
+
"step": 660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 4.32,
|
| 1200 |
+
"learning_rate": 8.259740259740259e-06,
|
| 1201 |
+
"loss": 1.7336,
|
| 1202 |
+
"step": 665
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.35,
|
| 1206 |
+
"learning_rate": 7.87012987012987e-06,
|
| 1207 |
+
"loss": 1.7146,
|
| 1208 |
+
"step": 670
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 4.38,
|
| 1212 |
+
"learning_rate": 7.48051948051948e-06,
|
| 1213 |
+
"loss": 1.7096,
|
| 1214 |
+
"step": 675
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.38,
|
| 1218 |
+
"eval_accuracy": 0.4215430163706026,
|
| 1219 |
+
"eval_loss": 3.9922502040863037,
|
| 1220 |
+
"eval_runtime": 17.1842,
|
| 1221 |
+
"eval_samples_per_second": 581.93,
|
| 1222 |
+
"eval_steps_per_second": 18.214,
|
| 1223 |
+
"step": 675
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 4.41,
|
| 1227 |
+
"learning_rate": 7.090909090909091e-06,
|
| 1228 |
+
"loss": 1.7183,
|
| 1229 |
+
"step": 680
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 4.45,
|
| 1233 |
+
"learning_rate": 6.701298701298701e-06,
|
| 1234 |
+
"loss": 1.7323,
|
| 1235 |
+
"step": 685
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 4.48,
|
| 1239 |
+
"learning_rate": 6.311688311688311e-06,
|
| 1240 |
+
"loss": 1.7087,
|
| 1241 |
+
"step": 690
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.48,
|
| 1245 |
+
"eval_accuracy": 0.42254440961337514,
|
| 1246 |
+
"eval_loss": 3.9751763343811035,
|
| 1247 |
+
"eval_runtime": 17.2048,
|
| 1248 |
+
"eval_samples_per_second": 581.233,
|
| 1249 |
+
"eval_steps_per_second": 18.193,
|
| 1250 |
+
"step": 690
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.51,
|
| 1254 |
+
"learning_rate": 5.9220779220779226e-06,
|
| 1255 |
+
"loss": 1.7267,
|
| 1256 |
+
"step": 695
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.54,
|
| 1260 |
+
"learning_rate": 5.532467532467533e-06,
|
| 1261 |
+
"loss": 1.6924,
|
| 1262 |
+
"step": 700
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.58,
|
| 1266 |
+
"learning_rate": 5.142857142857143e-06,
|
| 1267 |
+
"loss": 1.7101,
|
| 1268 |
+
"step": 705
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.58,
|
| 1272 |
+
"eval_accuracy": 0.42080285614768376,
|
| 1273 |
+
"eval_loss": 3.9924566745758057,
|
| 1274 |
+
"eval_runtime": 17.2206,
|
| 1275 |
+
"eval_samples_per_second": 580.699,
|
| 1276 |
+
"eval_steps_per_second": 18.176,
|
| 1277 |
+
"step": 705
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 4.61,
|
| 1281 |
+
"learning_rate": 4.7532467532467536e-06,
|
| 1282 |
+
"loss": 1.7133,
|
| 1283 |
+
"step": 710
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 4.64,
|
| 1287 |
+
"learning_rate": 4.363636363636364e-06,
|
| 1288 |
+
"loss": 1.7042,
|
| 1289 |
+
"step": 715
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 4.67,
|
| 1293 |
+
"learning_rate": 3.974025974025973e-06,
|
| 1294 |
+
"loss": 1.7061,
|
| 1295 |
+
"step": 720
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 4.67,
|
| 1299 |
+
"eval_accuracy": 0.4183211424590735,
|
| 1300 |
+
"eval_loss": 3.9925851821899414,
|
| 1301 |
+
"eval_runtime": 17.1622,
|
| 1302 |
+
"eval_samples_per_second": 582.675,
|
| 1303 |
+
"eval_steps_per_second": 18.238,
|
| 1304 |
+
"step": 720
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.71,
|
| 1308 |
+
"learning_rate": 3.5844155844155846e-06,
|
| 1309 |
+
"loss": 1.7194,
|
| 1310 |
+
"step": 725
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.74,
|
| 1314 |
+
"learning_rate": 3.194805194805195e-06,
|
| 1315 |
+
"loss": 1.7283,
|
| 1316 |
+
"step": 730
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.77,
|
| 1320 |
+
"learning_rate": 2.8051948051948052e-06,
|
| 1321 |
+
"loss": 1.7227,
|
| 1322 |
+
"step": 735
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.77,
|
| 1326 |
+
"eval_accuracy": 0.41671020550330895,
|
| 1327 |
+
"eval_loss": 4.021413326263428,
|
| 1328 |
+
"eval_runtime": 17.2026,
|
| 1329 |
+
"eval_samples_per_second": 581.308,
|
| 1330 |
+
"eval_steps_per_second": 18.195,
|
| 1331 |
+
"step": 735
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 4.77,
|
| 1335 |
+
"step": 735,
|
| 1336 |
+
"total_flos": 4.8027460072854234e+17,
|
| 1337 |
+
"train_loss": 2.085782461101506,
|
| 1338 |
+
"train_runtime": 24097.4857,
|
| 1339 |
+
"train_samples_per_second": 256.517,
|
| 1340 |
+
"train_steps_per_second": 0.032
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 4.77,
|
| 1344 |
+
"eval_accuracy": 0.4171891327063741,
|
| 1345 |
+
"eval_loss": 3.979358434677124,
|
| 1346 |
+
"eval_runtime": 17.2044,
|
| 1347 |
+
"eval_samples_per_second": 581.246,
|
| 1348 |
+
"eval_steps_per_second": 18.193,
|
| 1349 |
+
"step": 735
|
| 1350 |
+
}
|
| 1351 |
+
],
|
| 1352 |
+
"max_steps": 770,
|
| 1353 |
+
"num_train_epochs": 5,
|
| 1354 |
+
"total_flos": 4.8027460072854234e+17,
|
| 1355 |
+
"trial_name": null,
|
| 1356 |
+
"trial_params": null
|
| 1357 |
+
}
|