Training in progress, step 1200
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +2413 -5
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4736616809
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4f097c06024d14288c4d1c2bc97399ae4b68afab45866d17001b282195997bc
|
| 3 |
size 4736616809
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2368281769
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:485523d0b25487f4a3d1b4546753423187678c8f9d2e0c8e59a5bb81d3922724
|
| 3 |
size 2368281769
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3c9dc8981cc2c459913f24dacaaf669fa2a450e9a9a470b32679073465d6e3
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e9ea3b27fd701dd988bf6b88748faba7a045c4e47b69a9334392e6db3776b4
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "output/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -4822,11 +4822,2419 @@
|
|
| 4822 |
"eval_samples_per_second": 9.904,
|
| 4823 |
"eval_steps_per_second": 9.904,
|
| 4824 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4825 |
}
|
| 4826 |
],
|
| 4827 |
"max_steps": 5848,
|
| 4828 |
"num_train_epochs": 4,
|
| 4829 |
-
"total_flos":
|
| 4830 |
"trial_name": null,
|
| 4831 |
"trial_params": null
|
| 4832 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.987623929977417,
|
| 3 |
+
"best_model_checkpoint": "output/checkpoint-1200",
|
| 4 |
+
"epoch": 0.8204207861297611,
|
| 5 |
+
"global_step": 1200,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 4822 |
"eval_samples_per_second": 9.904,
|
| 4823 |
"eval_steps_per_second": 9.904,
|
| 4824 |
"step": 800
|
| 4825 |
+
},
|
| 4826 |
+
{
|
| 4827 |
+
"epoch": 0.55,
|
| 4828 |
+
"learning_rate": 0.0005361543909348441,
|
| 4829 |
+
"loss": 1.9264,
|
| 4830 |
+
"step": 801
|
| 4831 |
+
},
|
| 4832 |
+
{
|
| 4833 |
+
"epoch": 0.55,
|
| 4834 |
+
"learning_rate": 0.0005360481586402266,
|
| 4835 |
+
"loss": 1.8821,
|
| 4836 |
+
"step": 802
|
| 4837 |
+
},
|
| 4838 |
+
{
|
| 4839 |
+
"epoch": 0.55,
|
| 4840 |
+
"learning_rate": 0.000535941926345609,
|
| 4841 |
+
"loss": 2.0427,
|
| 4842 |
+
"step": 803
|
| 4843 |
+
},
|
| 4844 |
+
{
|
| 4845 |
+
"epoch": 0.55,
|
| 4846 |
+
"learning_rate": 0.0005358356940509915,
|
| 4847 |
+
"loss": 1.8675,
|
| 4848 |
+
"step": 804
|
| 4849 |
+
},
|
| 4850 |
+
{
|
| 4851 |
+
"epoch": 0.55,
|
| 4852 |
+
"learning_rate": 0.0005357294617563739,
|
| 4853 |
+
"loss": 1.9315,
|
| 4854 |
+
"step": 805
|
| 4855 |
+
},
|
| 4856 |
+
{
|
| 4857 |
+
"epoch": 0.55,
|
| 4858 |
+
"learning_rate": 0.0005356232294617563,
|
| 4859 |
+
"loss": 2.0091,
|
| 4860 |
+
"step": 806
|
| 4861 |
+
},
|
| 4862 |
+
{
|
| 4863 |
+
"epoch": 0.55,
|
| 4864 |
+
"learning_rate": 0.0005355169971671388,
|
| 4865 |
+
"loss": 1.9447,
|
| 4866 |
+
"step": 807
|
| 4867 |
+
},
|
| 4868 |
+
{
|
| 4869 |
+
"epoch": 0.55,
|
| 4870 |
+
"learning_rate": 0.0005354107648725212,
|
| 4871 |
+
"loss": 1.9089,
|
| 4872 |
+
"step": 808
|
| 4873 |
+
},
|
| 4874 |
+
{
|
| 4875 |
+
"epoch": 0.55,
|
| 4876 |
+
"learning_rate": 0.0005353045325779037,
|
| 4877 |
+
"loss": 1.8641,
|
| 4878 |
+
"step": 809
|
| 4879 |
+
},
|
| 4880 |
+
{
|
| 4881 |
+
"epoch": 0.55,
|
| 4882 |
+
"learning_rate": 0.000535198300283286,
|
| 4883 |
+
"loss": 1.858,
|
| 4884 |
+
"step": 810
|
| 4885 |
+
},
|
| 4886 |
+
{
|
| 4887 |
+
"epoch": 0.55,
|
| 4888 |
+
"learning_rate": 0.0005350920679886684,
|
| 4889 |
+
"loss": 1.9707,
|
| 4890 |
+
"step": 811
|
| 4891 |
+
},
|
| 4892 |
+
{
|
| 4893 |
+
"epoch": 0.56,
|
| 4894 |
+
"learning_rate": 0.0005349858356940509,
|
| 4895 |
+
"loss": 1.9646,
|
| 4896 |
+
"step": 812
|
| 4897 |
+
},
|
| 4898 |
+
{
|
| 4899 |
+
"epoch": 0.56,
|
| 4900 |
+
"learning_rate": 0.0005348796033994334,
|
| 4901 |
+
"loss": 1.8502,
|
| 4902 |
+
"step": 813
|
| 4903 |
+
},
|
| 4904 |
+
{
|
| 4905 |
+
"epoch": 0.56,
|
| 4906 |
+
"learning_rate": 0.0005347733711048158,
|
| 4907 |
+
"loss": 1.9738,
|
| 4908 |
+
"step": 814
|
| 4909 |
+
},
|
| 4910 |
+
{
|
| 4911 |
+
"epoch": 0.56,
|
| 4912 |
+
"learning_rate": 0.0005346671388101983,
|
| 4913 |
+
"loss": 1.9471,
|
| 4914 |
+
"step": 815
|
| 4915 |
+
},
|
| 4916 |
+
{
|
| 4917 |
+
"epoch": 0.56,
|
| 4918 |
+
"learning_rate": 0.0005345609065155807,
|
| 4919 |
+
"loss": 1.8659,
|
| 4920 |
+
"step": 816
|
| 4921 |
+
},
|
| 4922 |
+
{
|
| 4923 |
+
"epoch": 0.56,
|
| 4924 |
+
"learning_rate": 0.0005344546742209631,
|
| 4925 |
+
"loss": 1.8747,
|
| 4926 |
+
"step": 817
|
| 4927 |
+
},
|
| 4928 |
+
{
|
| 4929 |
+
"epoch": 0.56,
|
| 4930 |
+
"learning_rate": 0.0005343484419263456,
|
| 4931 |
+
"loss": 1.8295,
|
| 4932 |
+
"step": 818
|
| 4933 |
+
},
|
| 4934 |
+
{
|
| 4935 |
+
"epoch": 0.56,
|
| 4936 |
+
"learning_rate": 0.000534242209631728,
|
| 4937 |
+
"loss": 1.906,
|
| 4938 |
+
"step": 819
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 0.56,
|
| 4942 |
+
"learning_rate": 0.0005341359773371105,
|
| 4943 |
+
"loss": 1.9628,
|
| 4944 |
+
"step": 820
|
| 4945 |
+
},
|
| 4946 |
+
{
|
| 4947 |
+
"epoch": 0.56,
|
| 4948 |
+
"learning_rate": 0.0005340297450424929,
|
| 4949 |
+
"loss": 1.8916,
|
| 4950 |
+
"step": 821
|
| 4951 |
+
},
|
| 4952 |
+
{
|
| 4953 |
+
"epoch": 0.56,
|
| 4954 |
+
"learning_rate": 0.0005339235127478752,
|
| 4955 |
+
"loss": 1.9851,
|
| 4956 |
+
"step": 822
|
| 4957 |
+
},
|
| 4958 |
+
{
|
| 4959 |
+
"epoch": 0.56,
|
| 4960 |
+
"learning_rate": 0.0005338172804532577,
|
| 4961 |
+
"loss": 1.9781,
|
| 4962 |
+
"step": 823
|
| 4963 |
+
},
|
| 4964 |
+
{
|
| 4965 |
+
"epoch": 0.56,
|
| 4966 |
+
"learning_rate": 0.0005337110481586402,
|
| 4967 |
+
"loss": 1.8828,
|
| 4968 |
+
"step": 824
|
| 4969 |
+
},
|
| 4970 |
+
{
|
| 4971 |
+
"epoch": 0.56,
|
| 4972 |
+
"learning_rate": 0.0005336048158640226,
|
| 4973 |
+
"loss": 1.9323,
|
| 4974 |
+
"step": 825
|
| 4975 |
+
},
|
| 4976 |
+
{
|
| 4977 |
+
"epoch": 0.56,
|
| 4978 |
+
"learning_rate": 0.000533498583569405,
|
| 4979 |
+
"loss": 1.8749,
|
| 4980 |
+
"step": 826
|
| 4981 |
+
},
|
| 4982 |
+
{
|
| 4983 |
+
"epoch": 0.57,
|
| 4984 |
+
"learning_rate": 0.0005333923512747875,
|
| 4985 |
+
"loss": 1.9325,
|
| 4986 |
+
"step": 827
|
| 4987 |
+
},
|
| 4988 |
+
{
|
| 4989 |
+
"epoch": 0.57,
|
| 4990 |
+
"learning_rate": 0.0005332861189801699,
|
| 4991 |
+
"loss": 1.8826,
|
| 4992 |
+
"step": 828
|
| 4993 |
+
},
|
| 4994 |
+
{
|
| 4995 |
+
"epoch": 0.57,
|
| 4996 |
+
"learning_rate": 0.0005331798866855524,
|
| 4997 |
+
"loss": 1.9116,
|
| 4998 |
+
"step": 829
|
| 4999 |
+
},
|
| 5000 |
+
{
|
| 5001 |
+
"epoch": 0.57,
|
| 5002 |
+
"learning_rate": 0.0005330736543909348,
|
| 5003 |
+
"loss": 1.8078,
|
| 5004 |
+
"step": 830
|
| 5005 |
+
},
|
| 5006 |
+
{
|
| 5007 |
+
"epoch": 0.57,
|
| 5008 |
+
"learning_rate": 0.0005329674220963172,
|
| 5009 |
+
"loss": 1.8018,
|
| 5010 |
+
"step": 831
|
| 5011 |
+
},
|
| 5012 |
+
{
|
| 5013 |
+
"epoch": 0.57,
|
| 5014 |
+
"learning_rate": 0.0005328611898016997,
|
| 5015 |
+
"loss": 1.8972,
|
| 5016 |
+
"step": 832
|
| 5017 |
+
},
|
| 5018 |
+
{
|
| 5019 |
+
"epoch": 0.57,
|
| 5020 |
+
"learning_rate": 0.0005327549575070821,
|
| 5021 |
+
"loss": 1.88,
|
| 5022 |
+
"step": 833
|
| 5023 |
+
},
|
| 5024 |
+
{
|
| 5025 |
+
"epoch": 0.57,
|
| 5026 |
+
"learning_rate": 0.0005326487252124646,
|
| 5027 |
+
"loss": 1.8848,
|
| 5028 |
+
"step": 834
|
| 5029 |
+
},
|
| 5030 |
+
{
|
| 5031 |
+
"epoch": 0.57,
|
| 5032 |
+
"learning_rate": 0.000532542492917847,
|
| 5033 |
+
"loss": 1.9582,
|
| 5034 |
+
"step": 835
|
| 5035 |
+
},
|
| 5036 |
+
{
|
| 5037 |
+
"epoch": 0.57,
|
| 5038 |
+
"learning_rate": 0.0005324362606232294,
|
| 5039 |
+
"loss": 1.9269,
|
| 5040 |
+
"step": 836
|
| 5041 |
+
},
|
| 5042 |
+
{
|
| 5043 |
+
"epoch": 0.57,
|
| 5044 |
+
"learning_rate": 0.0005323300283286118,
|
| 5045 |
+
"loss": 2.041,
|
| 5046 |
+
"step": 837
|
| 5047 |
+
},
|
| 5048 |
+
{
|
| 5049 |
+
"epoch": 0.57,
|
| 5050 |
+
"learning_rate": 0.0005322237960339943,
|
| 5051 |
+
"loss": 2.0065,
|
| 5052 |
+
"step": 838
|
| 5053 |
+
},
|
| 5054 |
+
{
|
| 5055 |
+
"epoch": 0.57,
|
| 5056 |
+
"learning_rate": 0.0005321175637393767,
|
| 5057 |
+
"loss": 1.8516,
|
| 5058 |
+
"step": 839
|
| 5059 |
+
},
|
| 5060 |
+
{
|
| 5061 |
+
"epoch": 0.57,
|
| 5062 |
+
"learning_rate": 0.0005320113314447592,
|
| 5063 |
+
"loss": 1.913,
|
| 5064 |
+
"step": 840
|
| 5065 |
+
},
|
| 5066 |
+
{
|
| 5067 |
+
"epoch": 0.57,
|
| 5068 |
+
"learning_rate": 0.0005319050991501416,
|
| 5069 |
+
"loss": 1.9794,
|
| 5070 |
+
"step": 841
|
| 5071 |
+
},
|
| 5072 |
+
{
|
| 5073 |
+
"epoch": 0.58,
|
| 5074 |
+
"learning_rate": 0.000531798866855524,
|
| 5075 |
+
"loss": 1.9203,
|
| 5076 |
+
"step": 842
|
| 5077 |
+
},
|
| 5078 |
+
{
|
| 5079 |
+
"epoch": 0.58,
|
| 5080 |
+
"learning_rate": 0.0005316926345609065,
|
| 5081 |
+
"loss": 1.928,
|
| 5082 |
+
"step": 843
|
| 5083 |
+
},
|
| 5084 |
+
{
|
| 5085 |
+
"epoch": 0.58,
|
| 5086 |
+
"learning_rate": 0.0005315864022662889,
|
| 5087 |
+
"loss": 1.9136,
|
| 5088 |
+
"step": 844
|
| 5089 |
+
},
|
| 5090 |
+
{
|
| 5091 |
+
"epoch": 0.58,
|
| 5092 |
+
"learning_rate": 0.0005314801699716713,
|
| 5093 |
+
"loss": 1.9003,
|
| 5094 |
+
"step": 845
|
| 5095 |
+
},
|
| 5096 |
+
{
|
| 5097 |
+
"epoch": 0.58,
|
| 5098 |
+
"learning_rate": 0.0005313739376770538,
|
| 5099 |
+
"loss": 1.8607,
|
| 5100 |
+
"step": 846
|
| 5101 |
+
},
|
| 5102 |
+
{
|
| 5103 |
+
"epoch": 0.58,
|
| 5104 |
+
"learning_rate": 0.0005312677053824363,
|
| 5105 |
+
"loss": 1.9404,
|
| 5106 |
+
"step": 847
|
| 5107 |
+
},
|
| 5108 |
+
{
|
| 5109 |
+
"epoch": 0.58,
|
| 5110 |
+
"learning_rate": 0.0005311614730878186,
|
| 5111 |
+
"loss": 1.8756,
|
| 5112 |
+
"step": 848
|
| 5113 |
+
},
|
| 5114 |
+
{
|
| 5115 |
+
"epoch": 0.58,
|
| 5116 |
+
"learning_rate": 0.0005310552407932011,
|
| 5117 |
+
"loss": 1.9147,
|
| 5118 |
+
"step": 849
|
| 5119 |
+
},
|
| 5120 |
+
{
|
| 5121 |
+
"epoch": 0.58,
|
| 5122 |
+
"learning_rate": 0.0005309490084985835,
|
| 5123 |
+
"loss": 1.9053,
|
| 5124 |
+
"step": 850
|
| 5125 |
+
},
|
| 5126 |
+
{
|
| 5127 |
+
"epoch": 0.58,
|
| 5128 |
+
"learning_rate": 0.0005308427762039659,
|
| 5129 |
+
"loss": 1.8758,
|
| 5130 |
+
"step": 851
|
| 5131 |
+
},
|
| 5132 |
+
{
|
| 5133 |
+
"epoch": 0.58,
|
| 5134 |
+
"learning_rate": 0.0005307365439093484,
|
| 5135 |
+
"loss": 1.9473,
|
| 5136 |
+
"step": 852
|
| 5137 |
+
},
|
| 5138 |
+
{
|
| 5139 |
+
"epoch": 0.58,
|
| 5140 |
+
"learning_rate": 0.0005306303116147308,
|
| 5141 |
+
"loss": 1.8892,
|
| 5142 |
+
"step": 853
|
| 5143 |
+
},
|
| 5144 |
+
{
|
| 5145 |
+
"epoch": 0.58,
|
| 5146 |
+
"learning_rate": 0.0005305240793201133,
|
| 5147 |
+
"loss": 1.854,
|
| 5148 |
+
"step": 854
|
| 5149 |
+
},
|
| 5150 |
+
{
|
| 5151 |
+
"epoch": 0.58,
|
| 5152 |
+
"learning_rate": 0.0005304178470254957,
|
| 5153 |
+
"loss": 1.9216,
|
| 5154 |
+
"step": 855
|
| 5155 |
+
},
|
| 5156 |
+
{
|
| 5157 |
+
"epoch": 0.59,
|
| 5158 |
+
"learning_rate": 0.0005303116147308781,
|
| 5159 |
+
"loss": 1.9903,
|
| 5160 |
+
"step": 856
|
| 5161 |
+
},
|
| 5162 |
+
{
|
| 5163 |
+
"epoch": 0.59,
|
| 5164 |
+
"learning_rate": 0.0005302053824362606,
|
| 5165 |
+
"loss": 1.8707,
|
| 5166 |
+
"step": 857
|
| 5167 |
+
},
|
| 5168 |
+
{
|
| 5169 |
+
"epoch": 0.59,
|
| 5170 |
+
"learning_rate": 0.0005300991501416431,
|
| 5171 |
+
"loss": 1.9148,
|
| 5172 |
+
"step": 858
|
| 5173 |
+
},
|
| 5174 |
+
{
|
| 5175 |
+
"epoch": 0.59,
|
| 5176 |
+
"learning_rate": 0.0005299929178470255,
|
| 5177 |
+
"loss": 1.9627,
|
| 5178 |
+
"step": 859
|
| 5179 |
+
},
|
| 5180 |
+
{
|
| 5181 |
+
"epoch": 0.59,
|
| 5182 |
+
"learning_rate": 0.000529886685552408,
|
| 5183 |
+
"loss": 1.9643,
|
| 5184 |
+
"step": 860
|
| 5185 |
+
},
|
| 5186 |
+
{
|
| 5187 |
+
"epoch": 0.59,
|
| 5188 |
+
"learning_rate": 0.0005297804532577903,
|
| 5189 |
+
"loss": 1.9943,
|
| 5190 |
+
"step": 861
|
| 5191 |
+
},
|
| 5192 |
+
{
|
| 5193 |
+
"epoch": 0.59,
|
| 5194 |
+
"learning_rate": 0.0005296742209631727,
|
| 5195 |
+
"loss": 1.9124,
|
| 5196 |
+
"step": 862
|
| 5197 |
+
},
|
| 5198 |
+
{
|
| 5199 |
+
"epoch": 0.59,
|
| 5200 |
+
"learning_rate": 0.0005295679886685552,
|
| 5201 |
+
"loss": 1.9824,
|
| 5202 |
+
"step": 863
|
| 5203 |
+
},
|
| 5204 |
+
{
|
| 5205 |
+
"epoch": 0.59,
|
| 5206 |
+
"learning_rate": 0.0005294617563739376,
|
| 5207 |
+
"loss": 1.8462,
|
| 5208 |
+
"step": 864
|
| 5209 |
+
},
|
| 5210 |
+
{
|
| 5211 |
+
"epoch": 0.59,
|
| 5212 |
+
"learning_rate": 0.00052935552407932,
|
| 5213 |
+
"loss": 1.979,
|
| 5214 |
+
"step": 865
|
| 5215 |
+
},
|
| 5216 |
+
{
|
| 5217 |
+
"epoch": 0.59,
|
| 5218 |
+
"learning_rate": 0.0005292492917847025,
|
| 5219 |
+
"loss": 1.9432,
|
| 5220 |
+
"step": 866
|
| 5221 |
+
},
|
| 5222 |
+
{
|
| 5223 |
+
"epoch": 0.59,
|
| 5224 |
+
"learning_rate": 0.0005291430594900849,
|
| 5225 |
+
"loss": 1.8095,
|
| 5226 |
+
"step": 867
|
| 5227 |
+
},
|
| 5228 |
+
{
|
| 5229 |
+
"epoch": 0.59,
|
| 5230 |
+
"learning_rate": 0.0005290368271954674,
|
| 5231 |
+
"loss": 1.892,
|
| 5232 |
+
"step": 868
|
| 5233 |
+
},
|
| 5234 |
+
{
|
| 5235 |
+
"epoch": 0.59,
|
| 5236 |
+
"learning_rate": 0.0005289305949008499,
|
| 5237 |
+
"loss": 1.9231,
|
| 5238 |
+
"step": 869
|
| 5239 |
+
},
|
| 5240 |
+
{
|
| 5241 |
+
"epoch": 0.59,
|
| 5242 |
+
"learning_rate": 0.0005288243626062323,
|
| 5243 |
+
"loss": 1.995,
|
| 5244 |
+
"step": 870
|
| 5245 |
+
},
|
| 5246 |
+
{
|
| 5247 |
+
"epoch": 0.6,
|
| 5248 |
+
"learning_rate": 0.0005287181303116147,
|
| 5249 |
+
"loss": 1.9238,
|
| 5250 |
+
"step": 871
|
| 5251 |
+
},
|
| 5252 |
+
{
|
| 5253 |
+
"epoch": 0.6,
|
| 5254 |
+
"learning_rate": 0.0005286118980169971,
|
| 5255 |
+
"loss": 1.8531,
|
| 5256 |
+
"step": 872
|
| 5257 |
+
},
|
| 5258 |
+
{
|
| 5259 |
+
"epoch": 0.6,
|
| 5260 |
+
"learning_rate": 0.0005285056657223795,
|
| 5261 |
+
"loss": 1.9406,
|
| 5262 |
+
"step": 873
|
| 5263 |
+
},
|
| 5264 |
+
{
|
| 5265 |
+
"epoch": 0.6,
|
| 5266 |
+
"learning_rate": 0.000528399433427762,
|
| 5267 |
+
"loss": 1.8503,
|
| 5268 |
+
"step": 874
|
| 5269 |
+
},
|
| 5270 |
+
{
|
| 5271 |
+
"epoch": 0.6,
|
| 5272 |
+
"learning_rate": 0.0005282932011331444,
|
| 5273 |
+
"loss": 1.8353,
|
| 5274 |
+
"step": 875
|
| 5275 |
+
},
|
| 5276 |
+
{
|
| 5277 |
+
"epoch": 0.6,
|
| 5278 |
+
"learning_rate": 0.0005281869688385268,
|
| 5279 |
+
"loss": 1.8922,
|
| 5280 |
+
"step": 876
|
| 5281 |
+
},
|
| 5282 |
+
{
|
| 5283 |
+
"epoch": 0.6,
|
| 5284 |
+
"learning_rate": 0.0005280807365439093,
|
| 5285 |
+
"loss": 1.9666,
|
| 5286 |
+
"step": 877
|
| 5287 |
+
},
|
| 5288 |
+
{
|
| 5289 |
+
"epoch": 0.6,
|
| 5290 |
+
"learning_rate": 0.0005279745042492917,
|
| 5291 |
+
"loss": 2.0114,
|
| 5292 |
+
"step": 878
|
| 5293 |
+
},
|
| 5294 |
+
{
|
| 5295 |
+
"epoch": 0.6,
|
| 5296 |
+
"learning_rate": 0.0005278682719546742,
|
| 5297 |
+
"loss": 1.9562,
|
| 5298 |
+
"step": 879
|
| 5299 |
+
},
|
| 5300 |
+
{
|
| 5301 |
+
"epoch": 0.6,
|
| 5302 |
+
"learning_rate": 0.0005277620396600567,
|
| 5303 |
+
"loss": 1.9049,
|
| 5304 |
+
"step": 880
|
| 5305 |
+
},
|
| 5306 |
+
{
|
| 5307 |
+
"epoch": 0.6,
|
| 5308 |
+
"learning_rate": 0.0005276558073654391,
|
| 5309 |
+
"loss": 1.9307,
|
| 5310 |
+
"step": 881
|
| 5311 |
+
},
|
| 5312 |
+
{
|
| 5313 |
+
"epoch": 0.6,
|
| 5314 |
+
"learning_rate": 0.0005275495750708215,
|
| 5315 |
+
"loss": 2.001,
|
| 5316 |
+
"step": 882
|
| 5317 |
+
},
|
| 5318 |
+
{
|
| 5319 |
+
"epoch": 0.6,
|
| 5320 |
+
"learning_rate": 0.000527443342776204,
|
| 5321 |
+
"loss": 1.9832,
|
| 5322 |
+
"step": 883
|
| 5323 |
+
},
|
| 5324 |
+
{
|
| 5325 |
+
"epoch": 0.6,
|
| 5326 |
+
"learning_rate": 0.0005273371104815863,
|
| 5327 |
+
"loss": 1.928,
|
| 5328 |
+
"step": 884
|
| 5329 |
+
},
|
| 5330 |
+
{
|
| 5331 |
+
"epoch": 0.61,
|
| 5332 |
+
"learning_rate": 0.0005272308781869687,
|
| 5333 |
+
"loss": 1.959,
|
| 5334 |
+
"step": 885
|
| 5335 |
+
},
|
| 5336 |
+
{
|
| 5337 |
+
"epoch": 0.61,
|
| 5338 |
+
"learning_rate": 0.0005271246458923512,
|
| 5339 |
+
"loss": 1.9206,
|
| 5340 |
+
"step": 886
|
| 5341 |
+
},
|
| 5342 |
+
{
|
| 5343 |
+
"epoch": 0.61,
|
| 5344 |
+
"learning_rate": 0.0005270184135977336,
|
| 5345 |
+
"loss": 1.8442,
|
| 5346 |
+
"step": 887
|
| 5347 |
+
},
|
| 5348 |
+
{
|
| 5349 |
+
"epoch": 0.61,
|
| 5350 |
+
"learning_rate": 0.0005269121813031161,
|
| 5351 |
+
"loss": 1.7504,
|
| 5352 |
+
"step": 888
|
| 5353 |
+
},
|
| 5354 |
+
{
|
| 5355 |
+
"epoch": 0.61,
|
| 5356 |
+
"learning_rate": 0.0005268059490084985,
|
| 5357 |
+
"loss": 1.8934,
|
| 5358 |
+
"step": 889
|
| 5359 |
+
},
|
| 5360 |
+
{
|
| 5361 |
+
"epoch": 0.61,
|
| 5362 |
+
"learning_rate": 0.000526699716713881,
|
| 5363 |
+
"loss": 1.8794,
|
| 5364 |
+
"step": 890
|
| 5365 |
+
},
|
| 5366 |
+
{
|
| 5367 |
+
"epoch": 0.61,
|
| 5368 |
+
"learning_rate": 0.0005265934844192634,
|
| 5369 |
+
"loss": 1.8589,
|
| 5370 |
+
"step": 891
|
| 5371 |
+
},
|
| 5372 |
+
{
|
| 5373 |
+
"epoch": 0.61,
|
| 5374 |
+
"learning_rate": 0.0005264872521246459,
|
| 5375 |
+
"loss": 1.8441,
|
| 5376 |
+
"step": 892
|
| 5377 |
+
},
|
| 5378 |
+
{
|
| 5379 |
+
"epoch": 0.61,
|
| 5380 |
+
"learning_rate": 0.0005263810198300283,
|
| 5381 |
+
"loss": 1.8841,
|
| 5382 |
+
"step": 893
|
| 5383 |
+
},
|
| 5384 |
+
{
|
| 5385 |
+
"epoch": 0.61,
|
| 5386 |
+
"learning_rate": 0.0005262747875354108,
|
| 5387 |
+
"loss": 1.929,
|
| 5388 |
+
"step": 894
|
| 5389 |
+
},
|
| 5390 |
+
{
|
| 5391 |
+
"epoch": 0.61,
|
| 5392 |
+
"learning_rate": 0.0005261685552407932,
|
| 5393 |
+
"loss": 1.9099,
|
| 5394 |
+
"step": 895
|
| 5395 |
+
},
|
| 5396 |
+
{
|
| 5397 |
+
"epoch": 0.61,
|
| 5398 |
+
"learning_rate": 0.0005260623229461755,
|
| 5399 |
+
"loss": 1.8891,
|
| 5400 |
+
"step": 896
|
| 5401 |
+
},
|
| 5402 |
+
{
|
| 5403 |
+
"epoch": 0.61,
|
| 5404 |
+
"learning_rate": 0.000525956090651558,
|
| 5405 |
+
"loss": 1.9476,
|
| 5406 |
+
"step": 897
|
| 5407 |
+
},
|
| 5408 |
+
{
|
| 5409 |
+
"epoch": 0.61,
|
| 5410 |
+
"learning_rate": 0.0005258498583569404,
|
| 5411 |
+
"loss": 1.8918,
|
| 5412 |
+
"step": 898
|
| 5413 |
+
},
|
| 5414 |
+
{
|
| 5415 |
+
"epoch": 0.61,
|
| 5416 |
+
"learning_rate": 0.0005257436260623229,
|
| 5417 |
+
"loss": 1.9186,
|
| 5418 |
+
"step": 899
|
| 5419 |
+
},
|
| 5420 |
+
{
|
| 5421 |
+
"epoch": 0.62,
|
| 5422 |
+
"learning_rate": 0.0005256373937677053,
|
| 5423 |
+
"loss": 1.8635,
|
| 5424 |
+
"step": 900
|
| 5425 |
+
},
|
| 5426 |
+
{
|
| 5427 |
+
"epoch": 0.62,
|
| 5428 |
+
"learning_rate": 0.0005255311614730878,
|
| 5429 |
+
"loss": 2.0291,
|
| 5430 |
+
"step": 901
|
| 5431 |
+
},
|
| 5432 |
+
{
|
| 5433 |
+
"epoch": 0.62,
|
| 5434 |
+
"learning_rate": 0.0005254249291784702,
|
| 5435 |
+
"loss": 1.9284,
|
| 5436 |
+
"step": 902
|
| 5437 |
+
},
|
| 5438 |
+
{
|
| 5439 |
+
"epoch": 0.62,
|
| 5440 |
+
"learning_rate": 0.0005253186968838527,
|
| 5441 |
+
"loss": 1.8926,
|
| 5442 |
+
"step": 903
|
| 5443 |
+
},
|
| 5444 |
+
{
|
| 5445 |
+
"epoch": 0.62,
|
| 5446 |
+
"learning_rate": 0.0005252124645892351,
|
| 5447 |
+
"loss": 1.866,
|
| 5448 |
+
"step": 904
|
| 5449 |
+
},
|
| 5450 |
+
{
|
| 5451 |
+
"epoch": 0.62,
|
| 5452 |
+
"learning_rate": 0.0005251062322946175,
|
| 5453 |
+
"loss": 1.9719,
|
| 5454 |
+
"step": 905
|
| 5455 |
+
},
|
| 5456 |
+
{
|
| 5457 |
+
"epoch": 0.62,
|
| 5458 |
+
"learning_rate": 0.000525,
|
| 5459 |
+
"loss": 1.8531,
|
| 5460 |
+
"step": 906
|
| 5461 |
+
},
|
| 5462 |
+
{
|
| 5463 |
+
"epoch": 0.62,
|
| 5464 |
+
"learning_rate": 0.0005248937677053824,
|
| 5465 |
+
"loss": 1.9524,
|
| 5466 |
+
"step": 907
|
| 5467 |
+
},
|
| 5468 |
+
{
|
| 5469 |
+
"epoch": 0.62,
|
| 5470 |
+
"learning_rate": 0.0005247875354107649,
|
| 5471 |
+
"loss": 1.8973,
|
| 5472 |
+
"step": 908
|
| 5473 |
+
},
|
| 5474 |
+
{
|
| 5475 |
+
"epoch": 0.62,
|
| 5476 |
+
"learning_rate": 0.0005246813031161472,
|
| 5477 |
+
"loss": 1.8233,
|
| 5478 |
+
"step": 909
|
| 5479 |
+
},
|
| 5480 |
+
{
|
| 5481 |
+
"epoch": 0.62,
|
| 5482 |
+
"learning_rate": 0.0005245750708215296,
|
| 5483 |
+
"loss": 1.9966,
|
| 5484 |
+
"step": 910
|
| 5485 |
+
},
|
| 5486 |
+
{
|
| 5487 |
+
"epoch": 0.62,
|
| 5488 |
+
"learning_rate": 0.0005244688385269121,
|
| 5489 |
+
"loss": 1.9708,
|
| 5490 |
+
"step": 911
|
| 5491 |
+
},
|
| 5492 |
+
{
|
| 5493 |
+
"epoch": 0.62,
|
| 5494 |
+
"learning_rate": 0.0005243626062322946,
|
| 5495 |
+
"loss": 1.8901,
|
| 5496 |
+
"step": 912
|
| 5497 |
+
},
|
| 5498 |
+
{
|
| 5499 |
+
"epoch": 0.62,
|
| 5500 |
+
"learning_rate": 0.000524256373937677,
|
| 5501 |
+
"loss": 2.0427,
|
| 5502 |
+
"step": 913
|
| 5503 |
+
},
|
| 5504 |
+
{
|
| 5505 |
+
"epoch": 0.62,
|
| 5506 |
+
"learning_rate": 0.0005241501416430595,
|
| 5507 |
+
"loss": 1.7927,
|
| 5508 |
+
"step": 914
|
| 5509 |
+
},
|
| 5510 |
+
{
|
| 5511 |
+
"epoch": 0.63,
|
| 5512 |
+
"learning_rate": 0.0005240439093484419,
|
| 5513 |
+
"loss": 1.9332,
|
| 5514 |
+
"step": 915
|
| 5515 |
+
},
|
| 5516 |
+
{
|
| 5517 |
+
"epoch": 0.63,
|
| 5518 |
+
"learning_rate": 0.0005239376770538243,
|
| 5519 |
+
"loss": 1.9916,
|
| 5520 |
+
"step": 916
|
| 5521 |
+
},
|
| 5522 |
+
{
|
| 5523 |
+
"epoch": 0.63,
|
| 5524 |
+
"learning_rate": 0.0005238314447592068,
|
| 5525 |
+
"loss": 1.9279,
|
| 5526 |
+
"step": 917
|
| 5527 |
+
},
|
| 5528 |
+
{
|
| 5529 |
+
"epoch": 0.63,
|
| 5530 |
+
"learning_rate": 0.0005237252124645892,
|
| 5531 |
+
"loss": 1.8911,
|
| 5532 |
+
"step": 918
|
| 5533 |
+
},
|
| 5534 |
+
{
|
| 5535 |
+
"epoch": 0.63,
|
| 5536 |
+
"learning_rate": 0.0005236189801699717,
|
| 5537 |
+
"loss": 1.8922,
|
| 5538 |
+
"step": 919
|
| 5539 |
+
},
|
| 5540 |
+
{
|
| 5541 |
+
"epoch": 0.63,
|
| 5542 |
+
"learning_rate": 0.000523512747875354,
|
| 5543 |
+
"loss": 2.0017,
|
| 5544 |
+
"step": 920
|
| 5545 |
+
},
|
| 5546 |
+
{
|
| 5547 |
+
"epoch": 0.63,
|
| 5548 |
+
"learning_rate": 0.0005234065155807364,
|
| 5549 |
+
"loss": 1.9189,
|
| 5550 |
+
"step": 921
|
| 5551 |
+
},
|
| 5552 |
+
{
|
| 5553 |
+
"epoch": 0.63,
|
| 5554 |
+
"learning_rate": 0.0005233002832861189,
|
| 5555 |
+
"loss": 1.9797,
|
| 5556 |
+
"step": 922
|
| 5557 |
+
},
|
| 5558 |
+
{
|
| 5559 |
+
"epoch": 0.63,
|
| 5560 |
+
"learning_rate": 0.0005231940509915014,
|
| 5561 |
+
"loss": 1.9341,
|
| 5562 |
+
"step": 923
|
| 5563 |
+
},
|
| 5564 |
+
{
|
| 5565 |
+
"epoch": 0.63,
|
| 5566 |
+
"learning_rate": 0.0005230878186968838,
|
| 5567 |
+
"loss": 1.8676,
|
| 5568 |
+
"step": 924
|
| 5569 |
+
},
|
| 5570 |
+
{
|
| 5571 |
+
"epoch": 0.63,
|
| 5572 |
+
"learning_rate": 0.0005229815864022662,
|
| 5573 |
+
"loss": 2.0161,
|
| 5574 |
+
"step": 925
|
| 5575 |
+
},
|
| 5576 |
+
{
|
| 5577 |
+
"epoch": 0.63,
|
| 5578 |
+
"learning_rate": 0.0005228753541076487,
|
| 5579 |
+
"loss": 1.9621,
|
| 5580 |
+
"step": 926
|
| 5581 |
+
},
|
| 5582 |
+
{
|
| 5583 |
+
"epoch": 0.63,
|
| 5584 |
+
"learning_rate": 0.0005227691218130311,
|
| 5585 |
+
"loss": 1.9889,
|
| 5586 |
+
"step": 927
|
| 5587 |
+
},
|
| 5588 |
+
{
|
| 5589 |
+
"epoch": 0.63,
|
| 5590 |
+
"learning_rate": 0.0005226628895184136,
|
| 5591 |
+
"loss": 2.0333,
|
| 5592 |
+
"step": 928
|
| 5593 |
+
},
|
| 5594 |
+
{
|
| 5595 |
+
"epoch": 0.64,
|
| 5596 |
+
"learning_rate": 0.000522556657223796,
|
| 5597 |
+
"loss": 2.0584,
|
| 5598 |
+
"step": 929
|
| 5599 |
+
},
|
| 5600 |
+
{
|
| 5601 |
+
"epoch": 0.64,
|
| 5602 |
+
"learning_rate": 0.0005224504249291784,
|
| 5603 |
+
"loss": 1.8608,
|
| 5604 |
+
"step": 930
|
| 5605 |
+
},
|
| 5606 |
+
{
|
| 5607 |
+
"epoch": 0.64,
|
| 5608 |
+
"learning_rate": 0.0005223441926345609,
|
| 5609 |
+
"loss": 1.8649,
|
| 5610 |
+
"step": 931
|
| 5611 |
+
},
|
| 5612 |
+
{
|
| 5613 |
+
"epoch": 0.64,
|
| 5614 |
+
"learning_rate": 0.0005222379603399432,
|
| 5615 |
+
"loss": 1.9765,
|
| 5616 |
+
"step": 932
|
| 5617 |
+
},
|
| 5618 |
+
{
|
| 5619 |
+
"epoch": 0.64,
|
| 5620 |
+
"learning_rate": 0.0005221317280453257,
|
| 5621 |
+
"loss": 1.9244,
|
| 5622 |
+
"step": 933
|
| 5623 |
+
},
|
| 5624 |
+
{
|
| 5625 |
+
"epoch": 0.64,
|
| 5626 |
+
"learning_rate": 0.0005220254957507082,
|
| 5627 |
+
"loss": 1.9518,
|
| 5628 |
+
"step": 934
|
| 5629 |
+
},
|
| 5630 |
+
{
|
| 5631 |
+
"epoch": 0.64,
|
| 5632 |
+
"learning_rate": 0.0005219192634560906,
|
| 5633 |
+
"loss": 1.8535,
|
| 5634 |
+
"step": 935
|
| 5635 |
+
},
|
| 5636 |
+
{
|
| 5637 |
+
"epoch": 0.64,
|
| 5638 |
+
"learning_rate": 0.000521813031161473,
|
| 5639 |
+
"loss": 1.8148,
|
| 5640 |
+
"step": 936
|
| 5641 |
+
},
|
| 5642 |
+
{
|
| 5643 |
+
"epoch": 0.64,
|
| 5644 |
+
"learning_rate": 0.0005217067988668555,
|
| 5645 |
+
"loss": 1.881,
|
| 5646 |
+
"step": 937
|
| 5647 |
+
},
|
| 5648 |
+
{
|
| 5649 |
+
"epoch": 0.64,
|
| 5650 |
+
"learning_rate": 0.0005216005665722379,
|
| 5651 |
+
"loss": 1.9989,
|
| 5652 |
+
"step": 938
|
| 5653 |
+
},
|
| 5654 |
+
{
|
| 5655 |
+
"epoch": 0.64,
|
| 5656 |
+
"learning_rate": 0.0005214943342776204,
|
| 5657 |
+
"loss": 1.9885,
|
| 5658 |
+
"step": 939
|
| 5659 |
+
},
|
| 5660 |
+
{
|
| 5661 |
+
"epoch": 0.64,
|
| 5662 |
+
"learning_rate": 0.0005213881019830028,
|
| 5663 |
+
"loss": 1.9382,
|
| 5664 |
+
"step": 940
|
| 5665 |
+
},
|
| 5666 |
+
{
|
| 5667 |
+
"epoch": 0.64,
|
| 5668 |
+
"learning_rate": 0.0005212818696883852,
|
| 5669 |
+
"loss": 1.897,
|
| 5670 |
+
"step": 941
|
| 5671 |
+
},
|
| 5672 |
+
{
|
| 5673 |
+
"epoch": 0.64,
|
| 5674 |
+
"learning_rate": 0.0005211756373937677,
|
| 5675 |
+
"loss": 1.9608,
|
| 5676 |
+
"step": 942
|
| 5677 |
+
},
|
| 5678 |
+
{
|
| 5679 |
+
"epoch": 0.64,
|
| 5680 |
+
"learning_rate": 0.0005210694050991501,
|
| 5681 |
+
"loss": 2.0054,
|
| 5682 |
+
"step": 943
|
| 5683 |
+
},
|
| 5684 |
+
{
|
| 5685 |
+
"epoch": 0.65,
|
| 5686 |
+
"learning_rate": 0.0005209631728045324,
|
| 5687 |
+
"loss": 1.8902,
|
| 5688 |
+
"step": 944
|
| 5689 |
+
},
|
| 5690 |
+
{
|
| 5691 |
+
"epoch": 0.65,
|
| 5692 |
+
"learning_rate": 0.0005208569405099149,
|
| 5693 |
+
"loss": 1.887,
|
| 5694 |
+
"step": 945
|
| 5695 |
+
},
|
| 5696 |
+
{
|
| 5697 |
+
"epoch": 0.65,
|
| 5698 |
+
"learning_rate": 0.0005207507082152974,
|
| 5699 |
+
"loss": 1.8734,
|
| 5700 |
+
"step": 946
|
| 5701 |
+
},
|
| 5702 |
+
{
|
| 5703 |
+
"epoch": 0.65,
|
| 5704 |
+
"learning_rate": 0.0005206444759206798,
|
| 5705 |
+
"loss": 1.8166,
|
| 5706 |
+
"step": 947
|
| 5707 |
+
},
|
| 5708 |
+
{
|
| 5709 |
+
"epoch": 0.65,
|
| 5710 |
+
"learning_rate": 0.0005205382436260623,
|
| 5711 |
+
"loss": 1.9099,
|
| 5712 |
+
"step": 948
|
| 5713 |
+
},
|
| 5714 |
+
{
|
| 5715 |
+
"epoch": 0.65,
|
| 5716 |
+
"learning_rate": 0.0005204320113314447,
|
| 5717 |
+
"loss": 2.0139,
|
| 5718 |
+
"step": 949
|
| 5719 |
+
},
|
| 5720 |
+
{
|
| 5721 |
+
"epoch": 0.65,
|
| 5722 |
+
"learning_rate": 0.0005203257790368271,
|
| 5723 |
+
"loss": 1.8796,
|
| 5724 |
+
"step": 950
|
| 5725 |
+
},
|
| 5726 |
+
{
|
| 5727 |
+
"epoch": 0.65,
|
| 5728 |
+
"learning_rate": 0.0005202195467422096,
|
| 5729 |
+
"loss": 1.9342,
|
| 5730 |
+
"step": 951
|
| 5731 |
+
},
|
| 5732 |
+
{
|
| 5733 |
+
"epoch": 0.65,
|
| 5734 |
+
"learning_rate": 0.000520113314447592,
|
| 5735 |
+
"loss": 1.9592,
|
| 5736 |
+
"step": 952
|
| 5737 |
+
},
|
| 5738 |
+
{
|
| 5739 |
+
"epoch": 0.65,
|
| 5740 |
+
"learning_rate": 0.0005200070821529745,
|
| 5741 |
+
"loss": 1.9208,
|
| 5742 |
+
"step": 953
|
| 5743 |
+
},
|
| 5744 |
+
{
|
| 5745 |
+
"epoch": 0.65,
|
| 5746 |
+
"learning_rate": 0.0005199008498583569,
|
| 5747 |
+
"loss": 1.9498,
|
| 5748 |
+
"step": 954
|
| 5749 |
+
},
|
| 5750 |
+
{
|
| 5751 |
+
"epoch": 0.65,
|
| 5752 |
+
"learning_rate": 0.0005197946175637393,
|
| 5753 |
+
"loss": 1.9403,
|
| 5754 |
+
"step": 955
|
| 5755 |
+
},
|
| 5756 |
+
{
|
| 5757 |
+
"epoch": 0.65,
|
| 5758 |
+
"learning_rate": 0.0005196883852691218,
|
| 5759 |
+
"loss": 1.8585,
|
| 5760 |
+
"step": 956
|
| 5761 |
+
},
|
| 5762 |
+
{
|
| 5763 |
+
"epoch": 0.65,
|
| 5764 |
+
"learning_rate": 0.0005195821529745043,
|
| 5765 |
+
"loss": 1.8344,
|
| 5766 |
+
"step": 957
|
| 5767 |
+
},
|
| 5768 |
+
{
|
| 5769 |
+
"epoch": 0.65,
|
| 5770 |
+
"learning_rate": 0.0005194759206798866,
|
| 5771 |
+
"loss": 1.8947,
|
| 5772 |
+
"step": 958
|
| 5773 |
+
},
|
| 5774 |
+
{
|
| 5775 |
+
"epoch": 0.66,
|
| 5776 |
+
"learning_rate": 0.0005193696883852691,
|
| 5777 |
+
"loss": 2.0165,
|
| 5778 |
+
"step": 959
|
| 5779 |
+
},
|
| 5780 |
+
{
|
| 5781 |
+
"epoch": 0.66,
|
| 5782 |
+
"learning_rate": 0.0005192634560906515,
|
| 5783 |
+
"loss": 1.9441,
|
| 5784 |
+
"step": 960
|
| 5785 |
+
},
|
| 5786 |
+
{
|
| 5787 |
+
"epoch": 0.66,
|
| 5788 |
+
"learning_rate": 0.0005191572237960339,
|
| 5789 |
+
"loss": 1.9187,
|
| 5790 |
+
"step": 961
|
| 5791 |
+
},
|
| 5792 |
+
{
|
| 5793 |
+
"epoch": 0.66,
|
| 5794 |
+
"learning_rate": 0.0005190509915014164,
|
| 5795 |
+
"loss": 1.8554,
|
| 5796 |
+
"step": 962
|
| 5797 |
+
},
|
| 5798 |
+
{
|
| 5799 |
+
"epoch": 0.66,
|
| 5800 |
+
"learning_rate": 0.0005189447592067988,
|
| 5801 |
+
"loss": 1.9357,
|
| 5802 |
+
"step": 963
|
| 5803 |
+
},
|
| 5804 |
+
{
|
| 5805 |
+
"epoch": 0.66,
|
| 5806 |
+
"learning_rate": 0.0005188385269121813,
|
| 5807 |
+
"loss": 1.886,
|
| 5808 |
+
"step": 964
|
| 5809 |
+
},
|
| 5810 |
+
{
|
| 5811 |
+
"epoch": 0.66,
|
| 5812 |
+
"learning_rate": 0.0005187322946175637,
|
| 5813 |
+
"loss": 1.9487,
|
| 5814 |
+
"step": 965
|
| 5815 |
+
},
|
| 5816 |
+
{
|
| 5817 |
+
"epoch": 0.66,
|
| 5818 |
+
"learning_rate": 0.0005186260623229461,
|
| 5819 |
+
"loss": 2.0203,
|
| 5820 |
+
"step": 966
|
| 5821 |
+
},
|
| 5822 |
+
{
|
| 5823 |
+
"epoch": 0.66,
|
| 5824 |
+
"learning_rate": 0.0005185198300283286,
|
| 5825 |
+
"loss": 1.9021,
|
| 5826 |
+
"step": 967
|
| 5827 |
+
},
|
| 5828 |
+
{
|
| 5829 |
+
"epoch": 0.66,
|
| 5830 |
+
"learning_rate": 0.0005184135977337111,
|
| 5831 |
+
"loss": 1.8394,
|
| 5832 |
+
"step": 968
|
| 5833 |
+
},
|
| 5834 |
+
{
|
| 5835 |
+
"epoch": 0.66,
|
| 5836 |
+
"learning_rate": 0.0005183073654390935,
|
| 5837 |
+
"loss": 1.9888,
|
| 5838 |
+
"step": 969
|
| 5839 |
+
},
|
| 5840 |
+
{
|
| 5841 |
+
"epoch": 0.66,
|
| 5842 |
+
"learning_rate": 0.0005182011331444758,
|
| 5843 |
+
"loss": 1.9302,
|
| 5844 |
+
"step": 970
|
| 5845 |
+
},
|
| 5846 |
+
{
|
| 5847 |
+
"epoch": 0.66,
|
| 5848 |
+
"learning_rate": 0.0005180949008498583,
|
| 5849 |
+
"loss": 1.9058,
|
| 5850 |
+
"step": 971
|
| 5851 |
+
},
|
| 5852 |
+
{
|
| 5853 |
+
"epoch": 0.66,
|
| 5854 |
+
"learning_rate": 0.0005179886685552407,
|
| 5855 |
+
"loss": 1.9338,
|
| 5856 |
+
"step": 972
|
| 5857 |
+
},
|
| 5858 |
+
{
|
| 5859 |
+
"epoch": 0.67,
|
| 5860 |
+
"learning_rate": 0.0005178824362606232,
|
| 5861 |
+
"loss": 1.8802,
|
| 5862 |
+
"step": 973
|
| 5863 |
+
},
|
| 5864 |
+
{
|
| 5865 |
+
"epoch": 0.67,
|
| 5866 |
+
"learning_rate": 0.0005177762039660056,
|
| 5867 |
+
"loss": 1.9089,
|
| 5868 |
+
"step": 974
|
| 5869 |
+
},
|
| 5870 |
+
{
|
| 5871 |
+
"epoch": 0.67,
|
| 5872 |
+
"learning_rate": 0.000517669971671388,
|
| 5873 |
+
"loss": 1.846,
|
| 5874 |
+
"step": 975
|
| 5875 |
+
},
|
| 5876 |
+
{
|
| 5877 |
+
"epoch": 0.67,
|
| 5878 |
+
"learning_rate": 0.0005175637393767705,
|
| 5879 |
+
"loss": 1.9375,
|
| 5880 |
+
"step": 976
|
| 5881 |
+
},
|
| 5882 |
+
{
|
| 5883 |
+
"epoch": 0.67,
|
| 5884 |
+
"learning_rate": 0.0005174575070821529,
|
| 5885 |
+
"loss": 1.9994,
|
| 5886 |
+
"step": 977
|
| 5887 |
+
},
|
| 5888 |
+
{
|
| 5889 |
+
"epoch": 0.67,
|
| 5890 |
+
"learning_rate": 0.0005173512747875354,
|
| 5891 |
+
"loss": 1.9906,
|
| 5892 |
+
"step": 978
|
| 5893 |
+
},
|
| 5894 |
+
{
|
| 5895 |
+
"epoch": 0.67,
|
| 5896 |
+
"learning_rate": 0.0005172450424929179,
|
| 5897 |
+
"loss": 1.8686,
|
| 5898 |
+
"step": 979
|
| 5899 |
+
},
|
| 5900 |
+
{
|
| 5901 |
+
"epoch": 0.67,
|
| 5902 |
+
"learning_rate": 0.0005171388101983003,
|
| 5903 |
+
"loss": 2.0107,
|
| 5904 |
+
"step": 980
|
| 5905 |
+
},
|
| 5906 |
+
{
|
| 5907 |
+
"epoch": 0.67,
|
| 5908 |
+
"learning_rate": 0.0005170325779036827,
|
| 5909 |
+
"loss": 1.9346,
|
| 5910 |
+
"step": 981
|
| 5911 |
+
},
|
| 5912 |
+
{
|
| 5913 |
+
"epoch": 0.67,
|
| 5914 |
+
"learning_rate": 0.0005169263456090651,
|
| 5915 |
+
"loss": 1.8315,
|
| 5916 |
+
"step": 982
|
| 5917 |
+
},
|
| 5918 |
+
{
|
| 5919 |
+
"epoch": 0.67,
|
| 5920 |
+
"learning_rate": 0.0005168201133144475,
|
| 5921 |
+
"loss": 1.9107,
|
| 5922 |
+
"step": 983
|
| 5923 |
+
},
|
| 5924 |
+
{
|
| 5925 |
+
"epoch": 0.67,
|
| 5926 |
+
"learning_rate": 0.00051671388101983,
|
| 5927 |
+
"loss": 1.8907,
|
| 5928 |
+
"step": 984
|
| 5929 |
+
},
|
| 5930 |
+
{
|
| 5931 |
+
"epoch": 0.67,
|
| 5932 |
+
"learning_rate": 0.0005166076487252124,
|
| 5933 |
+
"loss": 1.8357,
|
| 5934 |
+
"step": 985
|
| 5935 |
+
},
|
| 5936 |
+
{
|
| 5937 |
+
"epoch": 0.67,
|
| 5938 |
+
"learning_rate": 0.0005165014164305948,
|
| 5939 |
+
"loss": 1.914,
|
| 5940 |
+
"step": 986
|
| 5941 |
+
},
|
| 5942 |
+
{
|
| 5943 |
+
"epoch": 0.67,
|
| 5944 |
+
"learning_rate": 0.0005163951841359773,
|
| 5945 |
+
"loss": 1.8738,
|
| 5946 |
+
"step": 987
|
| 5947 |
+
},
|
| 5948 |
+
{
|
| 5949 |
+
"epoch": 0.68,
|
| 5950 |
+
"learning_rate": 0.0005162889518413597,
|
| 5951 |
+
"loss": 1.925,
|
| 5952 |
+
"step": 988
|
| 5953 |
+
},
|
| 5954 |
+
{
|
| 5955 |
+
"epoch": 0.68,
|
| 5956 |
+
"learning_rate": 0.0005161827195467422,
|
| 5957 |
+
"loss": 1.9579,
|
| 5958 |
+
"step": 989
|
| 5959 |
+
},
|
| 5960 |
+
{
|
| 5961 |
+
"epoch": 0.68,
|
| 5962 |
+
"learning_rate": 0.0005160764872521246,
|
| 5963 |
+
"loss": 1.8535,
|
| 5964 |
+
"step": 990
|
| 5965 |
+
},
|
| 5966 |
+
{
|
| 5967 |
+
"epoch": 0.68,
|
| 5968 |
+
"learning_rate": 0.0005159702549575071,
|
| 5969 |
+
"loss": 1.8589,
|
| 5970 |
+
"step": 991
|
| 5971 |
+
},
|
| 5972 |
+
{
|
| 5973 |
+
"epoch": 0.68,
|
| 5974 |
+
"learning_rate": 0.0005158640226628895,
|
| 5975 |
+
"loss": 1.8919,
|
| 5976 |
+
"step": 992
|
| 5977 |
+
},
|
| 5978 |
+
{
|
| 5979 |
+
"epoch": 0.68,
|
| 5980 |
+
"learning_rate": 0.000515757790368272,
|
| 5981 |
+
"loss": 1.9084,
|
| 5982 |
+
"step": 993
|
| 5983 |
+
},
|
| 5984 |
+
{
|
| 5985 |
+
"epoch": 0.68,
|
| 5986 |
+
"learning_rate": 0.0005156515580736543,
|
| 5987 |
+
"loss": 1.9123,
|
| 5988 |
+
"step": 994
|
| 5989 |
+
},
|
| 5990 |
+
{
|
| 5991 |
+
"epoch": 0.68,
|
| 5992 |
+
"learning_rate": 0.0005155453257790367,
|
| 5993 |
+
"loss": 1.9736,
|
| 5994 |
+
"step": 995
|
| 5995 |
+
},
|
| 5996 |
+
{
|
| 5997 |
+
"epoch": 0.68,
|
| 5998 |
+
"learning_rate": 0.0005154390934844192,
|
| 5999 |
+
"loss": 1.852,
|
| 6000 |
+
"step": 996
|
| 6001 |
+
},
|
| 6002 |
+
{
|
| 6003 |
+
"epoch": 0.68,
|
| 6004 |
+
"learning_rate": 0.0005153328611898016,
|
| 6005 |
+
"loss": 1.8952,
|
| 6006 |
+
"step": 997
|
| 6007 |
+
},
|
| 6008 |
+
{
|
| 6009 |
+
"epoch": 0.68,
|
| 6010 |
+
"learning_rate": 0.0005152266288951841,
|
| 6011 |
+
"loss": 1.9945,
|
| 6012 |
+
"step": 998
|
| 6013 |
+
},
|
| 6014 |
+
{
|
| 6015 |
+
"epoch": 0.68,
|
| 6016 |
+
"learning_rate": 0.0005151203966005665,
|
| 6017 |
+
"loss": 1.9205,
|
| 6018 |
+
"step": 999
|
| 6019 |
+
},
|
| 6020 |
+
{
|
| 6021 |
+
"epoch": 0.68,
|
| 6022 |
+
"learning_rate": 0.000515014164305949,
|
| 6023 |
+
"loss": 1.8991,
|
| 6024 |
+
"step": 1000
|
| 6025 |
+
},
|
| 6026 |
+
{
|
| 6027 |
+
"epoch": 0.68,
|
| 6028 |
+
"learning_rate": 0.0005149079320113314,
|
| 6029 |
+
"loss": 1.9652,
|
| 6030 |
+
"step": 1001
|
| 6031 |
+
},
|
| 6032 |
+
{
|
| 6033 |
+
"epoch": 0.69,
|
| 6034 |
+
"learning_rate": 0.0005148016997167139,
|
| 6035 |
+
"loss": 1.8882,
|
| 6036 |
+
"step": 1002
|
| 6037 |
+
},
|
| 6038 |
+
{
|
| 6039 |
+
"epoch": 0.69,
|
| 6040 |
+
"learning_rate": 0.0005146954674220963,
|
| 6041 |
+
"loss": 1.8064,
|
| 6042 |
+
"step": 1003
|
| 6043 |
+
},
|
| 6044 |
+
{
|
| 6045 |
+
"epoch": 0.69,
|
| 6046 |
+
"learning_rate": 0.0005145892351274788,
|
| 6047 |
+
"loss": 1.9101,
|
| 6048 |
+
"step": 1004
|
| 6049 |
+
},
|
| 6050 |
+
{
|
| 6051 |
+
"epoch": 0.69,
|
| 6052 |
+
"learning_rate": 0.0005144830028328612,
|
| 6053 |
+
"loss": 1.9095,
|
| 6054 |
+
"step": 1005
|
| 6055 |
+
},
|
| 6056 |
+
{
|
| 6057 |
+
"epoch": 0.69,
|
| 6058 |
+
"learning_rate": 0.0005143767705382435,
|
| 6059 |
+
"loss": 1.7793,
|
| 6060 |
+
"step": 1006
|
| 6061 |
+
},
|
| 6062 |
+
{
|
| 6063 |
+
"epoch": 0.69,
|
| 6064 |
+
"learning_rate": 0.000514270538243626,
|
| 6065 |
+
"loss": 1.8314,
|
| 6066 |
+
"step": 1007
|
| 6067 |
+
},
|
| 6068 |
+
{
|
| 6069 |
+
"epoch": 0.69,
|
| 6070 |
+
"learning_rate": 0.0005141643059490084,
|
| 6071 |
+
"loss": 1.8174,
|
| 6072 |
+
"step": 1008
|
| 6073 |
+
},
|
| 6074 |
+
{
|
| 6075 |
+
"epoch": 0.69,
|
| 6076 |
+
"learning_rate": 0.0005140580736543908,
|
| 6077 |
+
"loss": 1.8951,
|
| 6078 |
+
"step": 1009
|
| 6079 |
+
},
|
| 6080 |
+
{
|
| 6081 |
+
"epoch": 0.69,
|
| 6082 |
+
"learning_rate": 0.0005139518413597733,
|
| 6083 |
+
"loss": 1.947,
|
| 6084 |
+
"step": 1010
|
| 6085 |
+
},
|
| 6086 |
+
{
|
| 6087 |
+
"epoch": 0.69,
|
| 6088 |
+
"learning_rate": 0.0005138456090651558,
|
| 6089 |
+
"loss": 1.9609,
|
| 6090 |
+
"step": 1011
|
| 6091 |
+
},
|
| 6092 |
+
{
|
| 6093 |
+
"epoch": 0.69,
|
| 6094 |
+
"learning_rate": 0.0005137393767705382,
|
| 6095 |
+
"loss": 1.9234,
|
| 6096 |
+
"step": 1012
|
| 6097 |
+
},
|
| 6098 |
+
{
|
| 6099 |
+
"epoch": 0.69,
|
| 6100 |
+
"learning_rate": 0.0005136331444759207,
|
| 6101 |
+
"loss": 1.9117,
|
| 6102 |
+
"step": 1013
|
| 6103 |
+
},
|
| 6104 |
+
{
|
| 6105 |
+
"epoch": 0.69,
|
| 6106 |
+
"learning_rate": 0.0005135269121813031,
|
| 6107 |
+
"loss": 1.9156,
|
| 6108 |
+
"step": 1014
|
| 6109 |
+
},
|
| 6110 |
+
{
|
| 6111 |
+
"epoch": 0.69,
|
| 6112 |
+
"learning_rate": 0.0005134206798866855,
|
| 6113 |
+
"loss": 1.9459,
|
| 6114 |
+
"step": 1015
|
| 6115 |
+
},
|
| 6116 |
+
{
|
| 6117 |
+
"epoch": 0.69,
|
| 6118 |
+
"learning_rate": 0.000513314447592068,
|
| 6119 |
+
"loss": 1.948,
|
| 6120 |
+
"step": 1016
|
| 6121 |
+
},
|
| 6122 |
+
{
|
| 6123 |
+
"epoch": 0.7,
|
| 6124 |
+
"learning_rate": 0.0005132082152974504,
|
| 6125 |
+
"loss": 1.8795,
|
| 6126 |
+
"step": 1017
|
| 6127 |
+
},
|
| 6128 |
+
{
|
| 6129 |
+
"epoch": 0.7,
|
| 6130 |
+
"learning_rate": 0.0005131019830028329,
|
| 6131 |
+
"loss": 2.0597,
|
| 6132 |
+
"step": 1018
|
| 6133 |
+
},
|
| 6134 |
+
{
|
| 6135 |
+
"epoch": 0.7,
|
| 6136 |
+
"learning_rate": 0.0005129957507082152,
|
| 6137 |
+
"loss": 1.9661,
|
| 6138 |
+
"step": 1019
|
| 6139 |
+
},
|
| 6140 |
+
{
|
| 6141 |
+
"epoch": 0.7,
|
| 6142 |
+
"learning_rate": 0.0005128895184135976,
|
| 6143 |
+
"loss": 1.9242,
|
| 6144 |
+
"step": 1020
|
| 6145 |
+
},
|
| 6146 |
+
{
|
| 6147 |
+
"epoch": 0.7,
|
| 6148 |
+
"learning_rate": 0.0005127832861189801,
|
| 6149 |
+
"loss": 1.9773,
|
| 6150 |
+
"step": 1021
|
| 6151 |
+
},
|
| 6152 |
+
{
|
| 6153 |
+
"epoch": 0.7,
|
| 6154 |
+
"learning_rate": 0.0005126770538243626,
|
| 6155 |
+
"loss": 2.0018,
|
| 6156 |
+
"step": 1022
|
| 6157 |
+
},
|
| 6158 |
+
{
|
| 6159 |
+
"epoch": 0.7,
|
| 6160 |
+
"learning_rate": 0.000512570821529745,
|
| 6161 |
+
"loss": 1.8503,
|
| 6162 |
+
"step": 1023
|
| 6163 |
+
},
|
| 6164 |
+
{
|
| 6165 |
+
"epoch": 0.7,
|
| 6166 |
+
"learning_rate": 0.0005124645892351275,
|
| 6167 |
+
"loss": 1.8622,
|
| 6168 |
+
"step": 1024
|
| 6169 |
+
},
|
| 6170 |
+
{
|
| 6171 |
+
"epoch": 0.7,
|
| 6172 |
+
"learning_rate": 0.0005123583569405099,
|
| 6173 |
+
"loss": 2.0041,
|
| 6174 |
+
"step": 1025
|
| 6175 |
+
},
|
| 6176 |
+
{
|
| 6177 |
+
"epoch": 0.7,
|
| 6178 |
+
"learning_rate": 0.0005122521246458923,
|
| 6179 |
+
"loss": 1.9051,
|
| 6180 |
+
"step": 1026
|
| 6181 |
+
},
|
| 6182 |
+
{
|
| 6183 |
+
"epoch": 0.7,
|
| 6184 |
+
"learning_rate": 0.0005121458923512748,
|
| 6185 |
+
"loss": 1.9256,
|
| 6186 |
+
"step": 1027
|
| 6187 |
+
},
|
| 6188 |
+
{
|
| 6189 |
+
"epoch": 0.7,
|
| 6190 |
+
"learning_rate": 0.0005120396600566572,
|
| 6191 |
+
"loss": 1.8081,
|
| 6192 |
+
"step": 1028
|
| 6193 |
+
},
|
| 6194 |
+
{
|
| 6195 |
+
"epoch": 0.7,
|
| 6196 |
+
"learning_rate": 0.0005119334277620396,
|
| 6197 |
+
"loss": 1.9711,
|
| 6198 |
+
"step": 1029
|
| 6199 |
+
},
|
| 6200 |
+
{
|
| 6201 |
+
"epoch": 0.7,
|
| 6202 |
+
"learning_rate": 0.000511827195467422,
|
| 6203 |
+
"loss": 1.8529,
|
| 6204 |
+
"step": 1030
|
| 6205 |
+
},
|
| 6206 |
+
{
|
| 6207 |
+
"epoch": 0.7,
|
| 6208 |
+
"learning_rate": 0.0005117209631728044,
|
| 6209 |
+
"loss": 1.9109,
|
| 6210 |
+
"step": 1031
|
| 6211 |
+
},
|
| 6212 |
+
{
|
| 6213 |
+
"epoch": 0.71,
|
| 6214 |
+
"learning_rate": 0.0005116147308781869,
|
| 6215 |
+
"loss": 1.8838,
|
| 6216 |
+
"step": 1032
|
| 6217 |
+
},
|
| 6218 |
+
{
|
| 6219 |
+
"epoch": 0.71,
|
| 6220 |
+
"learning_rate": 0.0005115084985835694,
|
| 6221 |
+
"loss": 1.9032,
|
| 6222 |
+
"step": 1033
|
| 6223 |
+
},
|
| 6224 |
+
{
|
| 6225 |
+
"epoch": 0.71,
|
| 6226 |
+
"learning_rate": 0.0005114022662889518,
|
| 6227 |
+
"loss": 1.9147,
|
| 6228 |
+
"step": 1034
|
| 6229 |
+
},
|
| 6230 |
+
{
|
| 6231 |
+
"epoch": 0.71,
|
| 6232 |
+
"learning_rate": 0.0005112960339943342,
|
| 6233 |
+
"loss": 1.9068,
|
| 6234 |
+
"step": 1035
|
| 6235 |
+
},
|
| 6236 |
+
{
|
| 6237 |
+
"epoch": 0.71,
|
| 6238 |
+
"learning_rate": 0.0005111898016997167,
|
| 6239 |
+
"loss": 1.9089,
|
| 6240 |
+
"step": 1036
|
| 6241 |
+
},
|
| 6242 |
+
{
|
| 6243 |
+
"epoch": 0.71,
|
| 6244 |
+
"learning_rate": 0.0005110835694050991,
|
| 6245 |
+
"loss": 1.9809,
|
| 6246 |
+
"step": 1037
|
| 6247 |
+
},
|
| 6248 |
+
{
|
| 6249 |
+
"epoch": 0.71,
|
| 6250 |
+
"learning_rate": 0.0005109773371104816,
|
| 6251 |
+
"loss": 1.9325,
|
| 6252 |
+
"step": 1038
|
| 6253 |
+
},
|
| 6254 |
+
{
|
| 6255 |
+
"epoch": 0.71,
|
| 6256 |
+
"learning_rate": 0.000510871104815864,
|
| 6257 |
+
"loss": 1.9286,
|
| 6258 |
+
"step": 1039
|
| 6259 |
+
},
|
| 6260 |
+
{
|
| 6261 |
+
"epoch": 0.71,
|
| 6262 |
+
"learning_rate": 0.0005107648725212464,
|
| 6263 |
+
"loss": 1.89,
|
| 6264 |
+
"step": 1040
|
| 6265 |
+
},
|
| 6266 |
+
{
|
| 6267 |
+
"epoch": 0.71,
|
| 6268 |
+
"learning_rate": 0.0005106586402266289,
|
| 6269 |
+
"loss": 1.8083,
|
| 6270 |
+
"step": 1041
|
| 6271 |
+
},
|
| 6272 |
+
{
|
| 6273 |
+
"epoch": 0.71,
|
| 6274 |
+
"learning_rate": 0.0005105524079320113,
|
| 6275 |
+
"loss": 1.9368,
|
| 6276 |
+
"step": 1042
|
| 6277 |
+
},
|
| 6278 |
+
{
|
| 6279 |
+
"epoch": 0.71,
|
| 6280 |
+
"learning_rate": 0.0005104461756373937,
|
| 6281 |
+
"loss": 1.8549,
|
| 6282 |
+
"step": 1043
|
| 6283 |
+
},
|
| 6284 |
+
{
|
| 6285 |
+
"epoch": 0.71,
|
| 6286 |
+
"learning_rate": 0.0005103399433427762,
|
| 6287 |
+
"loss": 1.9071,
|
| 6288 |
+
"step": 1044
|
| 6289 |
+
},
|
| 6290 |
+
{
|
| 6291 |
+
"epoch": 0.71,
|
| 6292 |
+
"learning_rate": 0.0005102337110481586,
|
| 6293 |
+
"loss": 1.8773,
|
| 6294 |
+
"step": 1045
|
| 6295 |
+
},
|
| 6296 |
+
{
|
| 6297 |
+
"epoch": 0.72,
|
| 6298 |
+
"learning_rate": 0.000510127478753541,
|
| 6299 |
+
"loss": 1.8871,
|
| 6300 |
+
"step": 1046
|
| 6301 |
+
},
|
| 6302 |
+
{
|
| 6303 |
+
"epoch": 0.72,
|
| 6304 |
+
"learning_rate": 0.0005100212464589235,
|
| 6305 |
+
"loss": 1.9191,
|
| 6306 |
+
"step": 1047
|
| 6307 |
+
},
|
| 6308 |
+
{
|
| 6309 |
+
"epoch": 0.72,
|
| 6310 |
+
"learning_rate": 0.0005099150141643059,
|
| 6311 |
+
"loss": 1.9498,
|
| 6312 |
+
"step": 1048
|
| 6313 |
+
},
|
| 6314 |
+
{
|
| 6315 |
+
"epoch": 0.72,
|
| 6316 |
+
"learning_rate": 0.0005098087818696883,
|
| 6317 |
+
"loss": 1.9836,
|
| 6318 |
+
"step": 1049
|
| 6319 |
+
},
|
| 6320 |
+
{
|
| 6321 |
+
"epoch": 0.72,
|
| 6322 |
+
"learning_rate": 0.0005097025495750708,
|
| 6323 |
+
"loss": 1.8851,
|
| 6324 |
+
"step": 1050
|
| 6325 |
+
},
|
| 6326 |
+
{
|
| 6327 |
+
"epoch": 0.72,
|
| 6328 |
+
"learning_rate": 0.0005095963172804532,
|
| 6329 |
+
"loss": 1.9971,
|
| 6330 |
+
"step": 1051
|
| 6331 |
+
},
|
| 6332 |
+
{
|
| 6333 |
+
"epoch": 0.72,
|
| 6334 |
+
"learning_rate": 0.0005094900849858357,
|
| 6335 |
+
"loss": 1.9359,
|
| 6336 |
+
"step": 1052
|
| 6337 |
+
},
|
| 6338 |
+
{
|
| 6339 |
+
"epoch": 0.72,
|
| 6340 |
+
"learning_rate": 0.0005093838526912181,
|
| 6341 |
+
"loss": 1.8921,
|
| 6342 |
+
"step": 1053
|
| 6343 |
+
},
|
| 6344 |
+
{
|
| 6345 |
+
"epoch": 0.72,
|
| 6346 |
+
"learning_rate": 0.0005092776203966004,
|
| 6347 |
+
"loss": 1.815,
|
| 6348 |
+
"step": 1054
|
| 6349 |
+
},
|
| 6350 |
+
{
|
| 6351 |
+
"epoch": 0.72,
|
| 6352 |
+
"learning_rate": 0.0005091713881019829,
|
| 6353 |
+
"loss": 1.8988,
|
| 6354 |
+
"step": 1055
|
| 6355 |
+
},
|
| 6356 |
+
{
|
| 6357 |
+
"epoch": 0.72,
|
| 6358 |
+
"learning_rate": 0.0005090651558073654,
|
| 6359 |
+
"loss": 1.8765,
|
| 6360 |
+
"step": 1056
|
| 6361 |
+
},
|
| 6362 |
+
{
|
| 6363 |
+
"epoch": 0.72,
|
| 6364 |
+
"learning_rate": 0.0005089589235127478,
|
| 6365 |
+
"loss": 1.9362,
|
| 6366 |
+
"step": 1057
|
| 6367 |
+
},
|
| 6368 |
+
{
|
| 6369 |
+
"epoch": 0.72,
|
| 6370 |
+
"learning_rate": 0.0005088526912181303,
|
| 6371 |
+
"loss": 1.9116,
|
| 6372 |
+
"step": 1058
|
| 6373 |
+
},
|
| 6374 |
+
{
|
| 6375 |
+
"epoch": 0.72,
|
| 6376 |
+
"learning_rate": 0.0005087464589235127,
|
| 6377 |
+
"loss": 1.8551,
|
| 6378 |
+
"step": 1059
|
| 6379 |
+
},
|
| 6380 |
+
{
|
| 6381 |
+
"epoch": 0.72,
|
| 6382 |
+
"learning_rate": 0.0005086402266288951,
|
| 6383 |
+
"loss": 1.9469,
|
| 6384 |
+
"step": 1060
|
| 6385 |
+
},
|
| 6386 |
+
{
|
| 6387 |
+
"epoch": 0.73,
|
| 6388 |
+
"learning_rate": 0.0005085339943342776,
|
| 6389 |
+
"loss": 1.8255,
|
| 6390 |
+
"step": 1061
|
| 6391 |
+
},
|
| 6392 |
+
{
|
| 6393 |
+
"epoch": 0.73,
|
| 6394 |
+
"learning_rate": 0.00050842776203966,
|
| 6395 |
+
"loss": 1.8748,
|
| 6396 |
+
"step": 1062
|
| 6397 |
+
},
|
| 6398 |
+
{
|
| 6399 |
+
"epoch": 0.73,
|
| 6400 |
+
"learning_rate": 0.0005083215297450425,
|
| 6401 |
+
"loss": 1.9767,
|
| 6402 |
+
"step": 1063
|
| 6403 |
+
},
|
| 6404 |
+
{
|
| 6405 |
+
"epoch": 0.73,
|
| 6406 |
+
"learning_rate": 0.0005082152974504249,
|
| 6407 |
+
"loss": 1.8532,
|
| 6408 |
+
"step": 1064
|
| 6409 |
+
},
|
| 6410 |
+
{
|
| 6411 |
+
"epoch": 0.73,
|
| 6412 |
+
"learning_rate": 0.0005081090651558073,
|
| 6413 |
+
"loss": 1.9841,
|
| 6414 |
+
"step": 1065
|
| 6415 |
+
},
|
| 6416 |
+
{
|
| 6417 |
+
"epoch": 0.73,
|
| 6418 |
+
"learning_rate": 0.0005080028328611898,
|
| 6419 |
+
"loss": 1.9048,
|
| 6420 |
+
"step": 1066
|
| 6421 |
+
},
|
| 6422 |
+
{
|
| 6423 |
+
"epoch": 0.73,
|
| 6424 |
+
"learning_rate": 0.0005078966005665723,
|
| 6425 |
+
"loss": 1.9636,
|
| 6426 |
+
"step": 1067
|
| 6427 |
+
},
|
| 6428 |
+
{
|
| 6429 |
+
"epoch": 0.73,
|
| 6430 |
+
"learning_rate": 0.0005077903682719546,
|
| 6431 |
+
"loss": 1.8621,
|
| 6432 |
+
"step": 1068
|
| 6433 |
+
},
|
| 6434 |
+
{
|
| 6435 |
+
"epoch": 0.73,
|
| 6436 |
+
"learning_rate": 0.000507684135977337,
|
| 6437 |
+
"loss": 1.8718,
|
| 6438 |
+
"step": 1069
|
| 6439 |
+
},
|
| 6440 |
+
{
|
| 6441 |
+
"epoch": 0.73,
|
| 6442 |
+
"learning_rate": 0.0005075779036827195,
|
| 6443 |
+
"loss": 2.0384,
|
| 6444 |
+
"step": 1070
|
| 6445 |
+
},
|
| 6446 |
+
{
|
| 6447 |
+
"epoch": 0.73,
|
| 6448 |
+
"learning_rate": 0.0005074716713881019,
|
| 6449 |
+
"loss": 1.9328,
|
| 6450 |
+
"step": 1071
|
| 6451 |
+
},
|
| 6452 |
+
{
|
| 6453 |
+
"epoch": 0.73,
|
| 6454 |
+
"learning_rate": 0.0005073654390934844,
|
| 6455 |
+
"loss": 1.8559,
|
| 6456 |
+
"step": 1072
|
| 6457 |
+
},
|
| 6458 |
+
{
|
| 6459 |
+
"epoch": 0.73,
|
| 6460 |
+
"learning_rate": 0.0005072592067988668,
|
| 6461 |
+
"loss": 1.8485,
|
| 6462 |
+
"step": 1073
|
| 6463 |
+
},
|
| 6464 |
+
{
|
| 6465 |
+
"epoch": 0.73,
|
| 6466 |
+
"learning_rate": 0.0005071529745042492,
|
| 6467 |
+
"loss": 1.9306,
|
| 6468 |
+
"step": 1074
|
| 6469 |
+
},
|
| 6470 |
+
{
|
| 6471 |
+
"epoch": 0.73,
|
| 6472 |
+
"learning_rate": 0.0005070467422096317,
|
| 6473 |
+
"loss": 1.9929,
|
| 6474 |
+
"step": 1075
|
| 6475 |
+
},
|
| 6476 |
+
{
|
| 6477 |
+
"epoch": 0.74,
|
| 6478 |
+
"learning_rate": 0.0005069405099150141,
|
| 6479 |
+
"loss": 1.9442,
|
| 6480 |
+
"step": 1076
|
| 6481 |
+
},
|
| 6482 |
+
{
|
| 6483 |
+
"epoch": 0.74,
|
| 6484 |
+
"learning_rate": 0.0005068342776203966,
|
| 6485 |
+
"loss": 1.869,
|
| 6486 |
+
"step": 1077
|
| 6487 |
+
},
|
| 6488 |
+
{
|
| 6489 |
+
"epoch": 0.74,
|
| 6490 |
+
"learning_rate": 0.0005067280453257791,
|
| 6491 |
+
"loss": 1.9625,
|
| 6492 |
+
"step": 1078
|
| 6493 |
+
},
|
| 6494 |
+
{
|
| 6495 |
+
"epoch": 0.74,
|
| 6496 |
+
"learning_rate": 0.0005066218130311615,
|
| 6497 |
+
"loss": 1.9757,
|
| 6498 |
+
"step": 1079
|
| 6499 |
+
},
|
| 6500 |
+
{
|
| 6501 |
+
"epoch": 0.74,
|
| 6502 |
+
"learning_rate": 0.0005065155807365438,
|
| 6503 |
+
"loss": 1.9721,
|
| 6504 |
+
"step": 1080
|
| 6505 |
+
},
|
| 6506 |
+
{
|
| 6507 |
+
"epoch": 0.74,
|
| 6508 |
+
"learning_rate": 0.0005064093484419263,
|
| 6509 |
+
"loss": 1.9313,
|
| 6510 |
+
"step": 1081
|
| 6511 |
+
},
|
| 6512 |
+
{
|
| 6513 |
+
"epoch": 0.74,
|
| 6514 |
+
"learning_rate": 0.0005063031161473087,
|
| 6515 |
+
"loss": 1.9032,
|
| 6516 |
+
"step": 1082
|
| 6517 |
+
},
|
| 6518 |
+
{
|
| 6519 |
+
"epoch": 0.74,
|
| 6520 |
+
"learning_rate": 0.0005061968838526912,
|
| 6521 |
+
"loss": 1.8946,
|
| 6522 |
+
"step": 1083
|
| 6523 |
+
},
|
| 6524 |
+
{
|
| 6525 |
+
"epoch": 0.74,
|
| 6526 |
+
"learning_rate": 0.0005060906515580736,
|
| 6527 |
+
"loss": 1.927,
|
| 6528 |
+
"step": 1084
|
| 6529 |
+
},
|
| 6530 |
+
{
|
| 6531 |
+
"epoch": 0.74,
|
| 6532 |
+
"learning_rate": 0.000505984419263456,
|
| 6533 |
+
"loss": 1.9355,
|
| 6534 |
+
"step": 1085
|
| 6535 |
+
},
|
| 6536 |
+
{
|
| 6537 |
+
"epoch": 0.74,
|
| 6538 |
+
"learning_rate": 0.0005058781869688385,
|
| 6539 |
+
"loss": 1.9144,
|
| 6540 |
+
"step": 1086
|
| 6541 |
+
},
|
| 6542 |
+
{
|
| 6543 |
+
"epoch": 0.74,
|
| 6544 |
+
"learning_rate": 0.0005057719546742209,
|
| 6545 |
+
"loss": 1.8711,
|
| 6546 |
+
"step": 1087
|
| 6547 |
+
},
|
| 6548 |
+
{
|
| 6549 |
+
"epoch": 0.74,
|
| 6550 |
+
"learning_rate": 0.0005056657223796033,
|
| 6551 |
+
"loss": 1.908,
|
| 6552 |
+
"step": 1088
|
| 6553 |
+
},
|
| 6554 |
+
{
|
| 6555 |
+
"epoch": 0.74,
|
| 6556 |
+
"learning_rate": 0.0005055594900849858,
|
| 6557 |
+
"loss": 1.8863,
|
| 6558 |
+
"step": 1089
|
| 6559 |
+
},
|
| 6560 |
+
{
|
| 6561 |
+
"epoch": 0.75,
|
| 6562 |
+
"learning_rate": 0.0005054532577903683,
|
| 6563 |
+
"loss": 1.8877,
|
| 6564 |
+
"step": 1090
|
| 6565 |
+
},
|
| 6566 |
+
{
|
| 6567 |
+
"epoch": 0.75,
|
| 6568 |
+
"learning_rate": 0.0005053470254957507,
|
| 6569 |
+
"loss": 1.9125,
|
| 6570 |
+
"step": 1091
|
| 6571 |
+
},
|
| 6572 |
+
{
|
| 6573 |
+
"epoch": 0.75,
|
| 6574 |
+
"learning_rate": 0.0005052407932011331,
|
| 6575 |
+
"loss": 1.9083,
|
| 6576 |
+
"step": 1092
|
| 6577 |
+
},
|
| 6578 |
+
{
|
| 6579 |
+
"epoch": 0.75,
|
| 6580 |
+
"learning_rate": 0.0005051345609065155,
|
| 6581 |
+
"loss": 1.9148,
|
| 6582 |
+
"step": 1093
|
| 6583 |
+
},
|
| 6584 |
+
{
|
| 6585 |
+
"epoch": 0.75,
|
| 6586 |
+
"learning_rate": 0.0005050283286118979,
|
| 6587 |
+
"loss": 1.9313,
|
| 6588 |
+
"step": 1094
|
| 6589 |
+
},
|
| 6590 |
+
{
|
| 6591 |
+
"epoch": 0.75,
|
| 6592 |
+
"learning_rate": 0.0005049220963172804,
|
| 6593 |
+
"loss": 1.9542,
|
| 6594 |
+
"step": 1095
|
| 6595 |
+
},
|
| 6596 |
+
{
|
| 6597 |
+
"epoch": 0.75,
|
| 6598 |
+
"learning_rate": 0.0005048158640226628,
|
| 6599 |
+
"loss": 1.8714,
|
| 6600 |
+
"step": 1096
|
| 6601 |
+
},
|
| 6602 |
+
{
|
| 6603 |
+
"epoch": 0.75,
|
| 6604 |
+
"learning_rate": 0.0005047096317280453,
|
| 6605 |
+
"loss": 1.9771,
|
| 6606 |
+
"step": 1097
|
| 6607 |
+
},
|
| 6608 |
+
{
|
| 6609 |
+
"epoch": 0.75,
|
| 6610 |
+
"learning_rate": 0.0005046033994334277,
|
| 6611 |
+
"loss": 1.8602,
|
| 6612 |
+
"step": 1098
|
| 6613 |
+
},
|
| 6614 |
+
{
|
| 6615 |
+
"epoch": 0.75,
|
| 6616 |
+
"learning_rate": 0.0005044971671388101,
|
| 6617 |
+
"loss": 1.8857,
|
| 6618 |
+
"step": 1099
|
| 6619 |
+
},
|
| 6620 |
+
{
|
| 6621 |
+
"epoch": 0.75,
|
| 6622 |
+
"learning_rate": 0.0005043909348441926,
|
| 6623 |
+
"loss": 1.8951,
|
| 6624 |
+
"step": 1100
|
| 6625 |
+
},
|
| 6626 |
+
{
|
| 6627 |
+
"epoch": 0.75,
|
| 6628 |
+
"learning_rate": 0.0005042847025495751,
|
| 6629 |
+
"loss": 1.9468,
|
| 6630 |
+
"step": 1101
|
| 6631 |
+
},
|
| 6632 |
+
{
|
| 6633 |
+
"epoch": 0.75,
|
| 6634 |
+
"learning_rate": 0.0005041784702549575,
|
| 6635 |
+
"loss": 1.8194,
|
| 6636 |
+
"step": 1102
|
| 6637 |
+
},
|
| 6638 |
+
{
|
| 6639 |
+
"epoch": 0.75,
|
| 6640 |
+
"learning_rate": 0.00050407223796034,
|
| 6641 |
+
"loss": 1.9466,
|
| 6642 |
+
"step": 1103
|
| 6643 |
+
},
|
| 6644 |
+
{
|
| 6645 |
+
"epoch": 0.75,
|
| 6646 |
+
"learning_rate": 0.0005039660056657223,
|
| 6647 |
+
"loss": 1.8048,
|
| 6648 |
+
"step": 1104
|
| 6649 |
+
},
|
| 6650 |
+
{
|
| 6651 |
+
"epoch": 0.76,
|
| 6652 |
+
"learning_rate": 0.0005038597733711047,
|
| 6653 |
+
"loss": 1.8586,
|
| 6654 |
+
"step": 1105
|
| 6655 |
+
},
|
| 6656 |
+
{
|
| 6657 |
+
"epoch": 0.76,
|
| 6658 |
+
"learning_rate": 0.0005037535410764872,
|
| 6659 |
+
"loss": 1.8783,
|
| 6660 |
+
"step": 1106
|
| 6661 |
+
},
|
| 6662 |
+
{
|
| 6663 |
+
"epoch": 0.76,
|
| 6664 |
+
"learning_rate": 0.0005036473087818696,
|
| 6665 |
+
"loss": 1.8999,
|
| 6666 |
+
"step": 1107
|
| 6667 |
+
},
|
| 6668 |
+
{
|
| 6669 |
+
"epoch": 0.76,
|
| 6670 |
+
"learning_rate": 0.000503541076487252,
|
| 6671 |
+
"loss": 1.9716,
|
| 6672 |
+
"step": 1108
|
| 6673 |
+
},
|
| 6674 |
+
{
|
| 6675 |
+
"epoch": 0.76,
|
| 6676 |
+
"learning_rate": 0.0005034348441926345,
|
| 6677 |
+
"loss": 1.9234,
|
| 6678 |
+
"step": 1109
|
| 6679 |
+
},
|
| 6680 |
+
{
|
| 6681 |
+
"epoch": 0.76,
|
| 6682 |
+
"learning_rate": 0.0005033286118980169,
|
| 6683 |
+
"loss": 1.9661,
|
| 6684 |
+
"step": 1110
|
| 6685 |
+
},
|
| 6686 |
+
{
|
| 6687 |
+
"epoch": 0.76,
|
| 6688 |
+
"learning_rate": 0.0005032223796033994,
|
| 6689 |
+
"loss": 1.9817,
|
| 6690 |
+
"step": 1111
|
| 6691 |
+
},
|
| 6692 |
+
{
|
| 6693 |
+
"epoch": 0.76,
|
| 6694 |
+
"learning_rate": 0.0005031161473087819,
|
| 6695 |
+
"loss": 1.9502,
|
| 6696 |
+
"step": 1112
|
| 6697 |
+
},
|
| 6698 |
+
{
|
| 6699 |
+
"epoch": 0.76,
|
| 6700 |
+
"learning_rate": 0.0005030099150141643,
|
| 6701 |
+
"loss": 1.9734,
|
| 6702 |
+
"step": 1113
|
| 6703 |
+
},
|
| 6704 |
+
{
|
| 6705 |
+
"epoch": 0.76,
|
| 6706 |
+
"learning_rate": 0.0005029036827195467,
|
| 6707 |
+
"loss": 1.8585,
|
| 6708 |
+
"step": 1114
|
| 6709 |
+
},
|
| 6710 |
+
{
|
| 6711 |
+
"epoch": 0.76,
|
| 6712 |
+
"learning_rate": 0.0005027974504249292,
|
| 6713 |
+
"loss": 1.9161,
|
| 6714 |
+
"step": 1115
|
| 6715 |
+
},
|
| 6716 |
+
{
|
| 6717 |
+
"epoch": 0.76,
|
| 6718 |
+
"learning_rate": 0.0005026912181303115,
|
| 6719 |
+
"loss": 1.9213,
|
| 6720 |
+
"step": 1116
|
| 6721 |
+
},
|
| 6722 |
+
{
|
| 6723 |
+
"epoch": 0.76,
|
| 6724 |
+
"learning_rate": 0.000502584985835694,
|
| 6725 |
+
"loss": 1.9839,
|
| 6726 |
+
"step": 1117
|
| 6727 |
+
},
|
| 6728 |
+
{
|
| 6729 |
+
"epoch": 0.76,
|
| 6730 |
+
"learning_rate": 0.0005024787535410764,
|
| 6731 |
+
"loss": 1.9189,
|
| 6732 |
+
"step": 1118
|
| 6733 |
+
},
|
| 6734 |
+
{
|
| 6735 |
+
"epoch": 0.77,
|
| 6736 |
+
"learning_rate": 0.0005023725212464588,
|
| 6737 |
+
"loss": 2.0178,
|
| 6738 |
+
"step": 1119
|
| 6739 |
+
},
|
| 6740 |
+
{
|
| 6741 |
+
"epoch": 0.77,
|
| 6742 |
+
"learning_rate": 0.0005022662889518413,
|
| 6743 |
+
"loss": 1.9683,
|
| 6744 |
+
"step": 1120
|
| 6745 |
+
},
|
| 6746 |
+
{
|
| 6747 |
+
"epoch": 0.77,
|
| 6748 |
+
"learning_rate": 0.0005021600566572237,
|
| 6749 |
+
"loss": 1.9482,
|
| 6750 |
+
"step": 1121
|
| 6751 |
+
},
|
| 6752 |
+
{
|
| 6753 |
+
"epoch": 0.77,
|
| 6754 |
+
"learning_rate": 0.0005020538243626062,
|
| 6755 |
+
"loss": 1.9666,
|
| 6756 |
+
"step": 1122
|
| 6757 |
+
},
|
| 6758 |
+
{
|
| 6759 |
+
"epoch": 0.77,
|
| 6760 |
+
"learning_rate": 0.0005019475920679887,
|
| 6761 |
+
"loss": 1.9685,
|
| 6762 |
+
"step": 1123
|
| 6763 |
+
},
|
| 6764 |
+
{
|
| 6765 |
+
"epoch": 0.77,
|
| 6766 |
+
"learning_rate": 0.0005018413597733711,
|
| 6767 |
+
"loss": 1.8652,
|
| 6768 |
+
"step": 1124
|
| 6769 |
+
},
|
| 6770 |
+
{
|
| 6771 |
+
"epoch": 0.77,
|
| 6772 |
+
"learning_rate": 0.0005017351274787535,
|
| 6773 |
+
"loss": 1.9892,
|
| 6774 |
+
"step": 1125
|
| 6775 |
+
},
|
| 6776 |
+
{
|
| 6777 |
+
"epoch": 0.77,
|
| 6778 |
+
"learning_rate": 0.000501628895184136,
|
| 6779 |
+
"loss": 1.8648,
|
| 6780 |
+
"step": 1126
|
| 6781 |
+
},
|
| 6782 |
+
{
|
| 6783 |
+
"epoch": 0.77,
|
| 6784 |
+
"learning_rate": 0.0005015226628895184,
|
| 6785 |
+
"loss": 1.9587,
|
| 6786 |
+
"step": 1127
|
| 6787 |
+
},
|
| 6788 |
+
{
|
| 6789 |
+
"epoch": 0.77,
|
| 6790 |
+
"learning_rate": 0.0005014164305949007,
|
| 6791 |
+
"loss": 1.9027,
|
| 6792 |
+
"step": 1128
|
| 6793 |
+
},
|
| 6794 |
+
{
|
| 6795 |
+
"epoch": 0.77,
|
| 6796 |
+
"learning_rate": 0.0005013101983002832,
|
| 6797 |
+
"loss": 1.8348,
|
| 6798 |
+
"step": 1129
|
| 6799 |
+
},
|
| 6800 |
+
{
|
| 6801 |
+
"epoch": 0.77,
|
| 6802 |
+
"learning_rate": 0.0005012039660056656,
|
| 6803 |
+
"loss": 1.9392,
|
| 6804 |
+
"step": 1130
|
| 6805 |
+
},
|
| 6806 |
+
{
|
| 6807 |
+
"epoch": 0.77,
|
| 6808 |
+
"learning_rate": 0.0005010977337110481,
|
| 6809 |
+
"loss": 1.9353,
|
| 6810 |
+
"step": 1131
|
| 6811 |
+
},
|
| 6812 |
+
{
|
| 6813 |
+
"epoch": 0.77,
|
| 6814 |
+
"learning_rate": 0.0005009915014164305,
|
| 6815 |
+
"loss": 1.8492,
|
| 6816 |
+
"step": 1132
|
| 6817 |
+
},
|
| 6818 |
+
{
|
| 6819 |
+
"epoch": 0.77,
|
| 6820 |
+
"learning_rate": 0.000500885269121813,
|
| 6821 |
+
"loss": 1.9305,
|
| 6822 |
+
"step": 1133
|
| 6823 |
+
},
|
| 6824 |
+
{
|
| 6825 |
+
"epoch": 0.78,
|
| 6826 |
+
"learning_rate": 0.0005007790368271954,
|
| 6827 |
+
"loss": 1.824,
|
| 6828 |
+
"step": 1134
|
| 6829 |
+
},
|
| 6830 |
+
{
|
| 6831 |
+
"epoch": 0.78,
|
| 6832 |
+
"learning_rate": 0.0005006728045325779,
|
| 6833 |
+
"loss": 1.8344,
|
| 6834 |
+
"step": 1135
|
| 6835 |
+
},
|
| 6836 |
+
{
|
| 6837 |
+
"epoch": 0.78,
|
| 6838 |
+
"learning_rate": 0.0005005665722379603,
|
| 6839 |
+
"loss": 1.9966,
|
| 6840 |
+
"step": 1136
|
| 6841 |
+
},
|
| 6842 |
+
{
|
| 6843 |
+
"epoch": 0.78,
|
| 6844 |
+
"learning_rate": 0.0005004603399433428,
|
| 6845 |
+
"loss": 1.9755,
|
| 6846 |
+
"step": 1137
|
| 6847 |
+
},
|
| 6848 |
+
{
|
| 6849 |
+
"epoch": 0.78,
|
| 6850 |
+
"learning_rate": 0.0005003541076487252,
|
| 6851 |
+
"loss": 1.9514,
|
| 6852 |
+
"step": 1138
|
| 6853 |
+
},
|
| 6854 |
+
{
|
| 6855 |
+
"epoch": 0.78,
|
| 6856 |
+
"learning_rate": 0.0005002478753541076,
|
| 6857 |
+
"loss": 1.876,
|
| 6858 |
+
"step": 1139
|
| 6859 |
+
},
|
| 6860 |
+
{
|
| 6861 |
+
"epoch": 0.78,
|
| 6862 |
+
"learning_rate": 0.00050014164305949,
|
| 6863 |
+
"loss": 1.8808,
|
| 6864 |
+
"step": 1140
|
| 6865 |
+
},
|
| 6866 |
+
{
|
| 6867 |
+
"epoch": 0.78,
|
| 6868 |
+
"learning_rate": 0.0005000354107648724,
|
| 6869 |
+
"loss": 1.8629,
|
| 6870 |
+
"step": 1141
|
| 6871 |
+
},
|
| 6872 |
+
{
|
| 6873 |
+
"epoch": 0.78,
|
| 6874 |
+
"learning_rate": 0.0004999291784702549,
|
| 6875 |
+
"loss": 1.8372,
|
| 6876 |
+
"step": 1142
|
| 6877 |
+
},
|
| 6878 |
+
{
|
| 6879 |
+
"epoch": 0.78,
|
| 6880 |
+
"learning_rate": 0.0004998229461756373,
|
| 6881 |
+
"loss": 1.9778,
|
| 6882 |
+
"step": 1143
|
| 6883 |
+
},
|
| 6884 |
+
{
|
| 6885 |
+
"epoch": 0.78,
|
| 6886 |
+
"learning_rate": 0.0004997167138810198,
|
| 6887 |
+
"loss": 1.9397,
|
| 6888 |
+
"step": 1144
|
| 6889 |
+
},
|
| 6890 |
+
{
|
| 6891 |
+
"epoch": 0.78,
|
| 6892 |
+
"learning_rate": 0.0004996104815864022,
|
| 6893 |
+
"loss": 1.9774,
|
| 6894 |
+
"step": 1145
|
| 6895 |
+
},
|
| 6896 |
+
{
|
| 6897 |
+
"epoch": 0.78,
|
| 6898 |
+
"learning_rate": 0.0004995042492917847,
|
| 6899 |
+
"loss": 1.8552,
|
| 6900 |
+
"step": 1146
|
| 6901 |
+
},
|
| 6902 |
+
{
|
| 6903 |
+
"epoch": 0.78,
|
| 6904 |
+
"learning_rate": 0.0004993980169971671,
|
| 6905 |
+
"loss": 1.8838,
|
| 6906 |
+
"step": 1147
|
| 6907 |
+
},
|
| 6908 |
+
{
|
| 6909 |
+
"epoch": 0.78,
|
| 6910 |
+
"learning_rate": 0.0004992917847025496,
|
| 6911 |
+
"loss": 1.981,
|
| 6912 |
+
"step": 1148
|
| 6913 |
+
},
|
| 6914 |
+
{
|
| 6915 |
+
"epoch": 0.79,
|
| 6916 |
+
"learning_rate": 0.000499185552407932,
|
| 6917 |
+
"loss": 1.987,
|
| 6918 |
+
"step": 1149
|
| 6919 |
+
},
|
| 6920 |
+
{
|
| 6921 |
+
"epoch": 0.79,
|
| 6922 |
+
"learning_rate": 0.0004990793201133144,
|
| 6923 |
+
"loss": 1.9077,
|
| 6924 |
+
"step": 1150
|
| 6925 |
+
},
|
| 6926 |
+
{
|
| 6927 |
+
"epoch": 0.79,
|
| 6928 |
+
"learning_rate": 0.0004989730878186969,
|
| 6929 |
+
"loss": 1.9345,
|
| 6930 |
+
"step": 1151
|
| 6931 |
+
},
|
| 6932 |
+
{
|
| 6933 |
+
"epoch": 0.79,
|
| 6934 |
+
"learning_rate": 0.0004988668555240793,
|
| 6935 |
+
"loss": 1.8886,
|
| 6936 |
+
"step": 1152
|
| 6937 |
+
},
|
| 6938 |
+
{
|
| 6939 |
+
"epoch": 0.79,
|
| 6940 |
+
"learning_rate": 0.0004987606232294616,
|
| 6941 |
+
"loss": 1.8028,
|
| 6942 |
+
"step": 1153
|
| 6943 |
+
},
|
| 6944 |
+
{
|
| 6945 |
+
"epoch": 0.79,
|
| 6946 |
+
"learning_rate": 0.0004986543909348441,
|
| 6947 |
+
"loss": 1.8515,
|
| 6948 |
+
"step": 1154
|
| 6949 |
+
},
|
| 6950 |
+
{
|
| 6951 |
+
"epoch": 0.79,
|
| 6952 |
+
"learning_rate": 0.0004985481586402266,
|
| 6953 |
+
"loss": 1.9281,
|
| 6954 |
+
"step": 1155
|
| 6955 |
+
},
|
| 6956 |
+
{
|
| 6957 |
+
"epoch": 0.79,
|
| 6958 |
+
"learning_rate": 0.000498441926345609,
|
| 6959 |
+
"loss": 1.9567,
|
| 6960 |
+
"step": 1156
|
| 6961 |
+
},
|
| 6962 |
+
{
|
| 6963 |
+
"epoch": 0.79,
|
| 6964 |
+
"learning_rate": 0.0004983356940509915,
|
| 6965 |
+
"loss": 1.8555,
|
| 6966 |
+
"step": 1157
|
| 6967 |
+
},
|
| 6968 |
+
{
|
| 6969 |
+
"epoch": 0.79,
|
| 6970 |
+
"learning_rate": 0.0004982294617563739,
|
| 6971 |
+
"loss": 1.9253,
|
| 6972 |
+
"step": 1158
|
| 6973 |
+
},
|
| 6974 |
+
{
|
| 6975 |
+
"epoch": 0.79,
|
| 6976 |
+
"learning_rate": 0.0004981232294617563,
|
| 6977 |
+
"loss": 1.9719,
|
| 6978 |
+
"step": 1159
|
| 6979 |
+
},
|
| 6980 |
+
{
|
| 6981 |
+
"epoch": 0.79,
|
| 6982 |
+
"learning_rate": 0.0004980169971671388,
|
| 6983 |
+
"loss": 1.934,
|
| 6984 |
+
"step": 1160
|
| 6985 |
+
},
|
| 6986 |
+
{
|
| 6987 |
+
"epoch": 0.79,
|
| 6988 |
+
"learning_rate": 0.0004979107648725212,
|
| 6989 |
+
"loss": 1.8554,
|
| 6990 |
+
"step": 1161
|
| 6991 |
+
},
|
| 6992 |
+
{
|
| 6993 |
+
"epoch": 0.79,
|
| 6994 |
+
"learning_rate": 0.0004978045325779037,
|
| 6995 |
+
"loss": 1.9549,
|
| 6996 |
+
"step": 1162
|
| 6997 |
+
},
|
| 6998 |
+
{
|
| 6999 |
+
"epoch": 0.8,
|
| 7000 |
+
"learning_rate": 0.0004976983002832861,
|
| 7001 |
+
"loss": 1.8785,
|
| 7002 |
+
"step": 1163
|
| 7003 |
+
},
|
| 7004 |
+
{
|
| 7005 |
+
"epoch": 0.8,
|
| 7006 |
+
"learning_rate": 0.0004975920679886684,
|
| 7007 |
+
"loss": 1.902,
|
| 7008 |
+
"step": 1164
|
| 7009 |
+
},
|
| 7010 |
+
{
|
| 7011 |
+
"epoch": 0.8,
|
| 7012 |
+
"learning_rate": 0.0004974858356940509,
|
| 7013 |
+
"loss": 1.8741,
|
| 7014 |
+
"step": 1165
|
| 7015 |
+
},
|
| 7016 |
+
{
|
| 7017 |
+
"epoch": 0.8,
|
| 7018 |
+
"learning_rate": 0.0004973796033994334,
|
| 7019 |
+
"loss": 1.9525,
|
| 7020 |
+
"step": 1166
|
| 7021 |
+
},
|
| 7022 |
+
{
|
| 7023 |
+
"epoch": 0.8,
|
| 7024 |
+
"learning_rate": 0.0004972733711048158,
|
| 7025 |
+
"loss": 1.8687,
|
| 7026 |
+
"step": 1167
|
| 7027 |
+
},
|
| 7028 |
+
{
|
| 7029 |
+
"epoch": 0.8,
|
| 7030 |
+
"learning_rate": 0.0004971671388101983,
|
| 7031 |
+
"loss": 1.9317,
|
| 7032 |
+
"step": 1168
|
| 7033 |
+
},
|
| 7034 |
+
{
|
| 7035 |
+
"epoch": 0.8,
|
| 7036 |
+
"learning_rate": 0.0004970609065155807,
|
| 7037 |
+
"loss": 1.937,
|
| 7038 |
+
"step": 1169
|
| 7039 |
+
},
|
| 7040 |
+
{
|
| 7041 |
+
"epoch": 0.8,
|
| 7042 |
+
"learning_rate": 0.0004969546742209631,
|
| 7043 |
+
"loss": 1.917,
|
| 7044 |
+
"step": 1170
|
| 7045 |
+
},
|
| 7046 |
+
{
|
| 7047 |
+
"epoch": 0.8,
|
| 7048 |
+
"learning_rate": 0.0004968484419263456,
|
| 7049 |
+
"loss": 1.9639,
|
| 7050 |
+
"step": 1171
|
| 7051 |
+
},
|
| 7052 |
+
{
|
| 7053 |
+
"epoch": 0.8,
|
| 7054 |
+
"learning_rate": 0.000496742209631728,
|
| 7055 |
+
"loss": 1.908,
|
| 7056 |
+
"step": 1172
|
| 7057 |
+
},
|
| 7058 |
+
{
|
| 7059 |
+
"epoch": 0.8,
|
| 7060 |
+
"learning_rate": 0.0004966359773371104,
|
| 7061 |
+
"loss": 1.8845,
|
| 7062 |
+
"step": 1173
|
| 7063 |
+
},
|
| 7064 |
+
{
|
| 7065 |
+
"epoch": 0.8,
|
| 7066 |
+
"learning_rate": 0.0004965297450424929,
|
| 7067 |
+
"loss": 1.9162,
|
| 7068 |
+
"step": 1174
|
| 7069 |
+
},
|
| 7070 |
+
{
|
| 7071 |
+
"epoch": 0.8,
|
| 7072 |
+
"learning_rate": 0.0004964235127478753,
|
| 7073 |
+
"loss": 1.921,
|
| 7074 |
+
"step": 1175
|
| 7075 |
+
},
|
| 7076 |
+
{
|
| 7077 |
+
"epoch": 0.8,
|
| 7078 |
+
"learning_rate": 0.0004963172804532578,
|
| 7079 |
+
"loss": 1.8296,
|
| 7080 |
+
"step": 1176
|
| 7081 |
+
},
|
| 7082 |
+
{
|
| 7083 |
+
"epoch": 0.8,
|
| 7084 |
+
"learning_rate": 0.0004962110481586403,
|
| 7085 |
+
"loss": 1.8656,
|
| 7086 |
+
"step": 1177
|
| 7087 |
+
},
|
| 7088 |
+
{
|
| 7089 |
+
"epoch": 0.81,
|
| 7090 |
+
"learning_rate": 0.0004961048158640226,
|
| 7091 |
+
"loss": 1.9953,
|
| 7092 |
+
"step": 1178
|
| 7093 |
+
},
|
| 7094 |
+
{
|
| 7095 |
+
"epoch": 0.81,
|
| 7096 |
+
"learning_rate": 0.000495998583569405,
|
| 7097 |
+
"loss": 1.8856,
|
| 7098 |
+
"step": 1179
|
| 7099 |
+
},
|
| 7100 |
+
{
|
| 7101 |
+
"epoch": 0.81,
|
| 7102 |
+
"learning_rate": 0.0004958923512747875,
|
| 7103 |
+
"loss": 1.9518,
|
| 7104 |
+
"step": 1180
|
| 7105 |
+
},
|
| 7106 |
+
{
|
| 7107 |
+
"epoch": 0.81,
|
| 7108 |
+
"learning_rate": 0.0004957861189801699,
|
| 7109 |
+
"loss": 1.9682,
|
| 7110 |
+
"step": 1181
|
| 7111 |
+
},
|
| 7112 |
+
{
|
| 7113 |
+
"epoch": 0.81,
|
| 7114 |
+
"learning_rate": 0.0004956798866855524,
|
| 7115 |
+
"loss": 1.9359,
|
| 7116 |
+
"step": 1182
|
| 7117 |
+
},
|
| 7118 |
+
{
|
| 7119 |
+
"epoch": 0.81,
|
| 7120 |
+
"learning_rate": 0.0004955736543909348,
|
| 7121 |
+
"loss": 1.7835,
|
| 7122 |
+
"step": 1183
|
| 7123 |
+
},
|
| 7124 |
+
{
|
| 7125 |
+
"epoch": 0.81,
|
| 7126 |
+
"learning_rate": 0.0004954674220963172,
|
| 7127 |
+
"loss": 2.0103,
|
| 7128 |
+
"step": 1184
|
| 7129 |
+
},
|
| 7130 |
+
{
|
| 7131 |
+
"epoch": 0.81,
|
| 7132 |
+
"learning_rate": 0.0004953611898016997,
|
| 7133 |
+
"loss": 2.0312,
|
| 7134 |
+
"step": 1185
|
| 7135 |
+
},
|
| 7136 |
+
{
|
| 7137 |
+
"epoch": 0.81,
|
| 7138 |
+
"learning_rate": 0.0004952549575070821,
|
| 7139 |
+
"loss": 1.9787,
|
| 7140 |
+
"step": 1186
|
| 7141 |
+
},
|
| 7142 |
+
{
|
| 7143 |
+
"epoch": 0.81,
|
| 7144 |
+
"learning_rate": 0.0004951487252124646,
|
| 7145 |
+
"loss": 1.9269,
|
| 7146 |
+
"step": 1187
|
| 7147 |
+
},
|
| 7148 |
+
{
|
| 7149 |
+
"epoch": 0.81,
|
| 7150 |
+
"learning_rate": 0.0004950424929178471,
|
| 7151 |
+
"loss": 1.8983,
|
| 7152 |
+
"step": 1188
|
| 7153 |
+
},
|
| 7154 |
+
{
|
| 7155 |
+
"epoch": 0.81,
|
| 7156 |
+
"learning_rate": 0.0004949362606232295,
|
| 7157 |
+
"loss": 1.9233,
|
| 7158 |
+
"step": 1189
|
| 7159 |
+
},
|
| 7160 |
+
{
|
| 7161 |
+
"epoch": 0.81,
|
| 7162 |
+
"learning_rate": 0.0004948300283286118,
|
| 7163 |
+
"loss": 1.9143,
|
| 7164 |
+
"step": 1190
|
| 7165 |
+
},
|
| 7166 |
+
{
|
| 7167 |
+
"epoch": 0.81,
|
| 7168 |
+
"learning_rate": 0.0004947237960339943,
|
| 7169 |
+
"loss": 1.9361,
|
| 7170 |
+
"step": 1191
|
| 7171 |
+
},
|
| 7172 |
+
{
|
| 7173 |
+
"epoch": 0.81,
|
| 7174 |
+
"learning_rate": 0.0004946175637393767,
|
| 7175 |
+
"loss": 2.0513,
|
| 7176 |
+
"step": 1192
|
| 7177 |
+
},
|
| 7178 |
+
{
|
| 7179 |
+
"epoch": 0.82,
|
| 7180 |
+
"learning_rate": 0.0004945113314447591,
|
| 7181 |
+
"loss": 1.8629,
|
| 7182 |
+
"step": 1193
|
| 7183 |
+
},
|
| 7184 |
+
{
|
| 7185 |
+
"epoch": 0.82,
|
| 7186 |
+
"learning_rate": 0.0004944050991501416,
|
| 7187 |
+
"loss": 1.9171,
|
| 7188 |
+
"step": 1194
|
| 7189 |
+
},
|
| 7190 |
+
{
|
| 7191 |
+
"epoch": 0.82,
|
| 7192 |
+
"learning_rate": 0.000494298866855524,
|
| 7193 |
+
"loss": 1.9711,
|
| 7194 |
+
"step": 1195
|
| 7195 |
+
},
|
| 7196 |
+
{
|
| 7197 |
+
"epoch": 0.82,
|
| 7198 |
+
"learning_rate": 0.0004941926345609065,
|
| 7199 |
+
"loss": 1.8462,
|
| 7200 |
+
"step": 1196
|
| 7201 |
+
},
|
| 7202 |
+
{
|
| 7203 |
+
"epoch": 0.82,
|
| 7204 |
+
"learning_rate": 0.0004940864022662889,
|
| 7205 |
+
"loss": 1.9059,
|
| 7206 |
+
"step": 1197
|
| 7207 |
+
},
|
| 7208 |
+
{
|
| 7209 |
+
"epoch": 0.82,
|
| 7210 |
+
"learning_rate": 0.0004939801699716713,
|
| 7211 |
+
"loss": 1.9364,
|
| 7212 |
+
"step": 1198
|
| 7213 |
+
},
|
| 7214 |
+
{
|
| 7215 |
+
"epoch": 0.82,
|
| 7216 |
+
"learning_rate": 0.0004938739376770538,
|
| 7217 |
+
"loss": 1.9621,
|
| 7218 |
+
"step": 1199
|
| 7219 |
+
},
|
| 7220 |
+
{
|
| 7221 |
+
"epoch": 0.82,
|
| 7222 |
+
"learning_rate": 0.0004937677053824363,
|
| 7223 |
+
"loss": 1.9355,
|
| 7224 |
+
"step": 1200
|
| 7225 |
+
},
|
| 7226 |
+
{
|
| 7227 |
+
"epoch": 0.82,
|
| 7228 |
+
"eval_loss": 1.987623929977417,
|
| 7229 |
+
"eval_runtime": 1467.5466,
|
| 7230 |
+
"eval_samples_per_second": 9.909,
|
| 7231 |
+
"eval_steps_per_second": 9.909,
|
| 7232 |
+
"step": 1200
|
| 7233 |
}
|
| 7234 |
],
|
| 7235 |
"max_steps": 5848,
|
| 7236 |
"num_train_epochs": 4,
|
| 7237 |
+
"total_flos": 1.469431232616066e+18,
|
| 7238 |
"trial_name": null,
|
| 7239 |
"trial_params": null
|
| 7240 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2368281769
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:485523d0b25487f4a3d1b4546753423187678c8f9d2e0c8e59a5bb81d3922724
|
| 3 |
size 2368281769
|