Training in progress, step 400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1885008480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea4d45498252b7c143bb7dae8d110f1f236765b3da87dad80ebd35ce427e76f9
|
| 3 |
size 1885008480
|
last-checkpoint/optimizer.pt
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 sha256:9d1c27f46251e22235cc85d9a8ecea3ff02bb5bccb46fed604763144a0cd392d
|
| 3 |
+
size 683358430
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc66eb8712c93ab501c2b8b71043ec8788ab8459fd6df384c5039b4d3bd8f331
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25d3d3c15cb09b099096a6e7e480d07f7ac79ecb8ab6d787a4c48afde0462e6b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 5,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1527,13 +1527,1533 @@
|
|
| 1527 |
"eval_samples_per_second": 4.321,
|
| 1528 |
"eval_steps_per_second": 0.553,
|
| 1529 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1530 |
}
|
| 1531 |
],
|
| 1532 |
"logging_steps": 1,
|
| 1533 |
-
"max_steps":
|
| 1534 |
-
"num_train_epochs":
|
| 1535 |
"save_steps": 200,
|
| 1536 |
-
"total_flos":
|
| 1537 |
"trial_name": null,
|
| 1538 |
"trial_params": null
|
| 1539 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.6,
|
| 5 |
"eval_steps": 5,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1527 |
"eval_samples_per_second": 4.321,
|
| 1528 |
"eval_steps_per_second": 0.553,
|
| 1529 |
"step": 200
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8,
|
| 1533 |
+
"learning_rate": 0.00016536082474226803,
|
| 1534 |
+
"loss": 0.6259,
|
| 1535 |
+
"step": 201
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.81,
|
| 1539 |
+
"learning_rate": 0.00016515463917525774,
|
| 1540 |
+
"loss": 0.8477,
|
| 1541 |
+
"step": 202
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.81,
|
| 1545 |
+
"learning_rate": 0.00016494845360824742,
|
| 1546 |
+
"loss": 0.9355,
|
| 1547 |
+
"step": 203
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.82,
|
| 1551 |
+
"learning_rate": 0.0001647422680412371,
|
| 1552 |
+
"loss": 0.7632,
|
| 1553 |
+
"step": 204
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 0.82,
|
| 1557 |
+
"learning_rate": 0.00016453608247422681,
|
| 1558 |
+
"loss": 0.5125,
|
| 1559 |
+
"step": 205
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.82,
|
| 1563 |
+
"eval_loss": 0.5757731795310974,
|
| 1564 |
+
"eval_runtime": 58.6641,
|
| 1565 |
+
"eval_samples_per_second": 4.262,
|
| 1566 |
+
"eval_steps_per_second": 0.545,
|
| 1567 |
+
"step": 205
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.82,
|
| 1571 |
+
"learning_rate": 0.0001643298969072165,
|
| 1572 |
+
"loss": 0.7234,
|
| 1573 |
+
"step": 206
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.83,
|
| 1577 |
+
"learning_rate": 0.00016412371134020618,
|
| 1578 |
+
"loss": 0.7542,
|
| 1579 |
+
"step": 207
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.83,
|
| 1583 |
+
"learning_rate": 0.0001639175257731959,
|
| 1584 |
+
"loss": 0.6394,
|
| 1585 |
+
"step": 208
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.84,
|
| 1589 |
+
"learning_rate": 0.00016371134020618558,
|
| 1590 |
+
"loss": 0.5565,
|
| 1591 |
+
"step": 209
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.84,
|
| 1595 |
+
"learning_rate": 0.00016350515463917526,
|
| 1596 |
+
"loss": 0.6834,
|
| 1597 |
+
"step": 210
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.84,
|
| 1601 |
+
"eval_loss": 0.5658813714981079,
|
| 1602 |
+
"eval_runtime": 58.24,
|
| 1603 |
+
"eval_samples_per_second": 4.293,
|
| 1604 |
+
"eval_steps_per_second": 0.549,
|
| 1605 |
+
"step": 210
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.84,
|
| 1609 |
+
"learning_rate": 0.00016329896907216494,
|
| 1610 |
+
"loss": 0.662,
|
| 1611 |
+
"step": 211
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.85,
|
| 1615 |
+
"learning_rate": 0.00016309278350515465,
|
| 1616 |
+
"loss": 0.5459,
|
| 1617 |
+
"step": 212
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.85,
|
| 1621 |
+
"learning_rate": 0.00016288659793814434,
|
| 1622 |
+
"loss": 0.6164,
|
| 1623 |
+
"step": 213
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.86,
|
| 1627 |
+
"learning_rate": 0.00016268041237113402,
|
| 1628 |
+
"loss": 0.6335,
|
| 1629 |
+
"step": 214
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.86,
|
| 1633 |
+
"learning_rate": 0.00016247422680412373,
|
| 1634 |
+
"loss": 0.5906,
|
| 1635 |
+
"step": 215
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.86,
|
| 1639 |
+
"eval_loss": 0.5624733567237854,
|
| 1640 |
+
"eval_runtime": 57.9447,
|
| 1641 |
+
"eval_samples_per_second": 4.314,
|
| 1642 |
+
"eval_steps_per_second": 0.552,
|
| 1643 |
+
"step": 215
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.86,
|
| 1647 |
+
"learning_rate": 0.00016226804123711341,
|
| 1648 |
+
"loss": 0.5621,
|
| 1649 |
+
"step": 216
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.87,
|
| 1653 |
+
"learning_rate": 0.0001620618556701031,
|
| 1654 |
+
"loss": 0.5567,
|
| 1655 |
+
"step": 217
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.87,
|
| 1659 |
+
"learning_rate": 0.00016185567010309278,
|
| 1660 |
+
"loss": 0.4252,
|
| 1661 |
+
"step": 218
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.88,
|
| 1665 |
+
"learning_rate": 0.0001616494845360825,
|
| 1666 |
+
"loss": 0.6901,
|
| 1667 |
+
"step": 219
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 0.88,
|
| 1671 |
+
"learning_rate": 0.00016144329896907217,
|
| 1672 |
+
"loss": 0.6321,
|
| 1673 |
+
"step": 220
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.88,
|
| 1677 |
+
"eval_loss": 0.5694482326507568,
|
| 1678 |
+
"eval_runtime": 58.2135,
|
| 1679 |
+
"eval_samples_per_second": 4.295,
|
| 1680 |
+
"eval_steps_per_second": 0.55,
|
| 1681 |
+
"step": 220
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.88,
|
| 1685 |
+
"learning_rate": 0.00016123711340206186,
|
| 1686 |
+
"loss": 0.6163,
|
| 1687 |
+
"step": 221
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.89,
|
| 1691 |
+
"learning_rate": 0.00016103092783505157,
|
| 1692 |
+
"loss": 0.4961,
|
| 1693 |
+
"step": 222
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.89,
|
| 1697 |
+
"learning_rate": 0.00016082474226804125,
|
| 1698 |
+
"loss": 0.5632,
|
| 1699 |
+
"step": 223
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.9,
|
| 1703 |
+
"learning_rate": 0.00016061855670103094,
|
| 1704 |
+
"loss": 0.4749,
|
| 1705 |
+
"step": 224
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.9,
|
| 1709 |
+
"learning_rate": 0.00016041237113402065,
|
| 1710 |
+
"loss": 0.495,
|
| 1711 |
+
"step": 225
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9,
|
| 1715 |
+
"eval_loss": 0.5669766664505005,
|
| 1716 |
+
"eval_runtime": 57.9014,
|
| 1717 |
+
"eval_samples_per_second": 4.318,
|
| 1718 |
+
"eval_steps_per_second": 0.553,
|
| 1719 |
+
"step": 225
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.9,
|
| 1723 |
+
"learning_rate": 0.00016020618556701033,
|
| 1724 |
+
"loss": 0.4442,
|
| 1725 |
+
"step": 226
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.91,
|
| 1729 |
+
"learning_rate": 0.00016,
|
| 1730 |
+
"loss": 0.526,
|
| 1731 |
+
"step": 227
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.91,
|
| 1735 |
+
"learning_rate": 0.0001597938144329897,
|
| 1736 |
+
"loss": 0.5636,
|
| 1737 |
+
"step": 228
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.92,
|
| 1741 |
+
"learning_rate": 0.0001595876288659794,
|
| 1742 |
+
"loss": 0.511,
|
| 1743 |
+
"step": 229
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.92,
|
| 1747 |
+
"learning_rate": 0.0001593814432989691,
|
| 1748 |
+
"loss": 0.5395,
|
| 1749 |
+
"step": 230
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.92,
|
| 1753 |
+
"eval_loss": 0.5704668164253235,
|
| 1754 |
+
"eval_runtime": 57.9046,
|
| 1755 |
+
"eval_samples_per_second": 4.317,
|
| 1756 |
+
"eval_steps_per_second": 0.553,
|
| 1757 |
+
"step": 230
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.92,
|
| 1761 |
+
"learning_rate": 0.00015917525773195875,
|
| 1762 |
+
"loss": 0.5187,
|
| 1763 |
+
"step": 231
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.93,
|
| 1767 |
+
"learning_rate": 0.00015896907216494846,
|
| 1768 |
+
"loss": 0.5611,
|
| 1769 |
+
"step": 232
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 0.93,
|
| 1773 |
+
"learning_rate": 0.00015876288659793814,
|
| 1774 |
+
"loss": 0.4718,
|
| 1775 |
+
"step": 233
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.94,
|
| 1779 |
+
"learning_rate": 0.00015855670103092782,
|
| 1780 |
+
"loss": 0.4049,
|
| 1781 |
+
"step": 234
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.94,
|
| 1785 |
+
"learning_rate": 0.00015835051546391754,
|
| 1786 |
+
"loss": 0.5668,
|
| 1787 |
+
"step": 235
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.94,
|
| 1791 |
+
"eval_loss": 0.5722946524620056,
|
| 1792 |
+
"eval_runtime": 58.2566,
|
| 1793 |
+
"eval_samples_per_second": 4.291,
|
| 1794 |
+
"eval_steps_per_second": 0.549,
|
| 1795 |
+
"step": 235
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.94,
|
| 1799 |
+
"learning_rate": 0.00015814432989690722,
|
| 1800 |
+
"loss": 0.5245,
|
| 1801 |
+
"step": 236
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.95,
|
| 1805 |
+
"learning_rate": 0.0001579381443298969,
|
| 1806 |
+
"loss": 0.4994,
|
| 1807 |
+
"step": 237
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.95,
|
| 1811 |
+
"learning_rate": 0.0001577319587628866,
|
| 1812 |
+
"loss": 0.4223,
|
| 1813 |
+
"step": 238
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 0.96,
|
| 1817 |
+
"learning_rate": 0.0001575257731958763,
|
| 1818 |
+
"loss": 0.5222,
|
| 1819 |
+
"step": 239
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.96,
|
| 1823 |
+
"learning_rate": 0.00015731958762886598,
|
| 1824 |
+
"loss": 0.4199,
|
| 1825 |
+
"step": 240
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.96,
|
| 1829 |
+
"eval_loss": 0.5722372531890869,
|
| 1830 |
+
"eval_runtime": 57.804,
|
| 1831 |
+
"eval_samples_per_second": 4.325,
|
| 1832 |
+
"eval_steps_per_second": 0.554,
|
| 1833 |
+
"step": 240
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.96,
|
| 1837 |
+
"learning_rate": 0.00015711340206185566,
|
| 1838 |
+
"loss": 0.4171,
|
| 1839 |
+
"step": 241
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.97,
|
| 1843 |
+
"learning_rate": 0.00015690721649484537,
|
| 1844 |
+
"loss": 0.3978,
|
| 1845 |
+
"step": 242
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.97,
|
| 1849 |
+
"learning_rate": 0.00015690721649484537,
|
| 1850 |
+
"loss": 0.5726,
|
| 1851 |
+
"step": 243
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.98,
|
| 1855 |
+
"learning_rate": 0.00015670103092783506,
|
| 1856 |
+
"loss": 0.3324,
|
| 1857 |
+
"step": 244
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.98,
|
| 1861 |
+
"learning_rate": 0.00015649484536082474,
|
| 1862 |
+
"loss": 0.4253,
|
| 1863 |
+
"step": 245
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.98,
|
| 1867 |
+
"eval_loss": 0.5949168801307678,
|
| 1868 |
+
"eval_runtime": 58.1262,
|
| 1869 |
+
"eval_samples_per_second": 4.301,
|
| 1870 |
+
"eval_steps_per_second": 0.551,
|
| 1871 |
+
"step": 245
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.98,
|
| 1875 |
+
"learning_rate": 0.00015628865979381445,
|
| 1876 |
+
"loss": 0.3992,
|
| 1877 |
+
"step": 246
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.99,
|
| 1881 |
+
"learning_rate": 0.00015608247422680413,
|
| 1882 |
+
"loss": 0.4968,
|
| 1883 |
+
"step": 247
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 0.99,
|
| 1887 |
+
"learning_rate": 0.00015587628865979382,
|
| 1888 |
+
"loss": 0.388,
|
| 1889 |
+
"step": 248
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 1.0,
|
| 1893 |
+
"learning_rate": 0.0001556701030927835,
|
| 1894 |
+
"loss": 0.3071,
|
| 1895 |
+
"step": 249
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 1.0,
|
| 1899 |
+
"learning_rate": 0.0001554639175257732,
|
| 1900 |
+
"loss": 0.4561,
|
| 1901 |
+
"step": 250
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.0,
|
| 1905 |
+
"eval_loss": 0.6334843039512634,
|
| 1906 |
+
"eval_runtime": 58.0783,
|
| 1907 |
+
"eval_samples_per_second": 4.305,
|
| 1908 |
+
"eval_steps_per_second": 0.551,
|
| 1909 |
+
"step": 250
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 1.0,
|
| 1913 |
+
"learning_rate": 0.0001552577319587629,
|
| 1914 |
+
"loss": 0.8641,
|
| 1915 |
+
"step": 251
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 1.01,
|
| 1919 |
+
"learning_rate": 0.00015505154639175258,
|
| 1920 |
+
"loss": 0.5815,
|
| 1921 |
+
"step": 252
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.01,
|
| 1925 |
+
"learning_rate": 0.0001548453608247423,
|
| 1926 |
+
"loss": 0.6515,
|
| 1927 |
+
"step": 253
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.02,
|
| 1931 |
+
"learning_rate": 0.00015463917525773197,
|
| 1932 |
+
"loss": 0.6192,
|
| 1933 |
+
"step": 254
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.02,
|
| 1937 |
+
"learning_rate": 0.00015443298969072166,
|
| 1938 |
+
"loss": 0.4681,
|
| 1939 |
+
"step": 255
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.02,
|
| 1943 |
+
"eval_loss": 0.5661035776138306,
|
| 1944 |
+
"eval_runtime": 58.219,
|
| 1945 |
+
"eval_samples_per_second": 4.294,
|
| 1946 |
+
"eval_steps_per_second": 0.55,
|
| 1947 |
+
"step": 255
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.02,
|
| 1951 |
+
"learning_rate": 0.00015422680412371137,
|
| 1952 |
+
"loss": 0.5288,
|
| 1953 |
+
"step": 256
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.03,
|
| 1957 |
+
"learning_rate": 0.00015402061855670105,
|
| 1958 |
+
"loss": 0.4924,
|
| 1959 |
+
"step": 257
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.03,
|
| 1963 |
+
"learning_rate": 0.00015381443298969073,
|
| 1964 |
+
"loss": 0.5358,
|
| 1965 |
+
"step": 258
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.04,
|
| 1969 |
+
"learning_rate": 0.00015360824742268042,
|
| 1970 |
+
"loss": 0.5082,
|
| 1971 |
+
"step": 259
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 1.04,
|
| 1975 |
+
"learning_rate": 0.00015340206185567013,
|
| 1976 |
+
"loss": 0.4527,
|
| 1977 |
+
"step": 260
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.04,
|
| 1981 |
+
"eval_loss": 0.5820726156234741,
|
| 1982 |
+
"eval_runtime": 57.7612,
|
| 1983 |
+
"eval_samples_per_second": 4.328,
|
| 1984 |
+
"eval_steps_per_second": 0.554,
|
| 1985 |
+
"step": 260
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 1.04,
|
| 1989 |
+
"learning_rate": 0.0001531958762886598,
|
| 1990 |
+
"loss": 0.5516,
|
| 1991 |
+
"step": 261
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.05,
|
| 1995 |
+
"learning_rate": 0.00015298969072164947,
|
| 1996 |
+
"loss": 0.5131,
|
| 1997 |
+
"step": 262
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.05,
|
| 2001 |
+
"learning_rate": 0.00015278350515463918,
|
| 2002 |
+
"loss": 0.5988,
|
| 2003 |
+
"step": 263
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.06,
|
| 2007 |
+
"learning_rate": 0.00015257731958762886,
|
| 2008 |
+
"loss": 0.4569,
|
| 2009 |
+
"step": 264
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 1.06,
|
| 2013 |
+
"learning_rate": 0.00015237113402061855,
|
| 2014 |
+
"loss": 0.53,
|
| 2015 |
+
"step": 265
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 1.06,
|
| 2019 |
+
"eval_loss": 0.5718860030174255,
|
| 2020 |
+
"eval_runtime": 58.2455,
|
| 2021 |
+
"eval_samples_per_second": 4.292,
|
| 2022 |
+
"eval_steps_per_second": 0.549,
|
| 2023 |
+
"step": 265
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 1.06,
|
| 2027 |
+
"learning_rate": 0.00015216494845360826,
|
| 2028 |
+
"loss": 0.506,
|
| 2029 |
+
"step": 266
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 1.07,
|
| 2033 |
+
"learning_rate": 0.00015195876288659794,
|
| 2034 |
+
"loss": 0.5774,
|
| 2035 |
+
"step": 267
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 1.07,
|
| 2039 |
+
"learning_rate": 0.00015175257731958762,
|
| 2040 |
+
"loss": 0.3699,
|
| 2041 |
+
"step": 268
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 1.08,
|
| 2045 |
+
"learning_rate": 0.00015154639175257733,
|
| 2046 |
+
"loss": 0.3874,
|
| 2047 |
+
"step": 269
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.08,
|
| 2051 |
+
"learning_rate": 0.00015134020618556702,
|
| 2052 |
+
"loss": 0.552,
|
| 2053 |
+
"step": 270
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.08,
|
| 2057 |
+
"eval_loss": 0.5731833577156067,
|
| 2058 |
+
"eval_runtime": 58.0655,
|
| 2059 |
+
"eval_samples_per_second": 4.305,
|
| 2060 |
+
"eval_steps_per_second": 0.551,
|
| 2061 |
+
"step": 270
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.08,
|
| 2065 |
+
"learning_rate": 0.0001511340206185567,
|
| 2066 |
+
"loss": 0.4844,
|
| 2067 |
+
"step": 271
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.09,
|
| 2071 |
+
"learning_rate": 0.00015092783505154638,
|
| 2072 |
+
"loss": 0.4164,
|
| 2073 |
+
"step": 272
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.09,
|
| 2077 |
+
"learning_rate": 0.0001507216494845361,
|
| 2078 |
+
"loss": 0.4694,
|
| 2079 |
+
"step": 273
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.1,
|
| 2083 |
+
"learning_rate": 0.00015051546391752578,
|
| 2084 |
+
"loss": 0.4008,
|
| 2085 |
+
"step": 274
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 1.1,
|
| 2089 |
+
"learning_rate": 0.00015030927835051546,
|
| 2090 |
+
"loss": 0.4439,
|
| 2091 |
+
"step": 275
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 1.1,
|
| 2095 |
+
"eval_loss": 0.5790666341781616,
|
| 2096 |
+
"eval_runtime": 57.8801,
|
| 2097 |
+
"eval_samples_per_second": 4.319,
|
| 2098 |
+
"eval_steps_per_second": 0.553,
|
| 2099 |
+
"step": 275
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 1.1,
|
| 2103 |
+
"learning_rate": 0.00015010309278350517,
|
| 2104 |
+
"loss": 0.4399,
|
| 2105 |
+
"step": 276
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 1.11,
|
| 2109 |
+
"learning_rate": 0.00014989690721649486,
|
| 2110 |
+
"loss": 0.4316,
|
| 2111 |
+
"step": 277
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 1.11,
|
| 2115 |
+
"learning_rate": 0.00014969072164948454,
|
| 2116 |
+
"loss": 0.4761,
|
| 2117 |
+
"step": 278
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.12,
|
| 2121 |
+
"learning_rate": 0.00014948453608247422,
|
| 2122 |
+
"loss": 0.44,
|
| 2123 |
+
"step": 279
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.12,
|
| 2127 |
+
"learning_rate": 0.00014927835051546393,
|
| 2128 |
+
"loss": 0.3519,
|
| 2129 |
+
"step": 280
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 1.12,
|
| 2133 |
+
"eval_loss": 0.5812113881111145,
|
| 2134 |
+
"eval_runtime": 58.0042,
|
| 2135 |
+
"eval_samples_per_second": 4.31,
|
| 2136 |
+
"eval_steps_per_second": 0.552,
|
| 2137 |
+
"step": 280
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.12,
|
| 2141 |
+
"learning_rate": 0.00014907216494845362,
|
| 2142 |
+
"loss": 0.3776,
|
| 2143 |
+
"step": 281
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 1.13,
|
| 2147 |
+
"learning_rate": 0.0001488659793814433,
|
| 2148 |
+
"loss": 0.3389,
|
| 2149 |
+
"step": 282
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 1.13,
|
| 2153 |
+
"learning_rate": 0.000148659793814433,
|
| 2154 |
+
"loss": 0.3219,
|
| 2155 |
+
"step": 283
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 1.14,
|
| 2159 |
+
"learning_rate": 0.0001484536082474227,
|
| 2160 |
+
"loss": 0.4546,
|
| 2161 |
+
"step": 284
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 1.14,
|
| 2165 |
+
"learning_rate": 0.00014824742268041238,
|
| 2166 |
+
"loss": 0.4285,
|
| 2167 |
+
"step": 285
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 1.14,
|
| 2171 |
+
"eval_loss": 0.5796990990638733,
|
| 2172 |
+
"eval_runtime": 57.8331,
|
| 2173 |
+
"eval_samples_per_second": 4.323,
|
| 2174 |
+
"eval_steps_per_second": 0.553,
|
| 2175 |
+
"step": 285
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 1.14,
|
| 2179 |
+
"learning_rate": 0.0001480412371134021,
|
| 2180 |
+
"loss": 0.3603,
|
| 2181 |
+
"step": 286
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 1.15,
|
| 2185 |
+
"learning_rate": 0.00014783505154639177,
|
| 2186 |
+
"loss": 0.3516,
|
| 2187 |
+
"step": 287
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.15,
|
| 2191 |
+
"learning_rate": 0.00014762886597938146,
|
| 2192 |
+
"loss": 0.3092,
|
| 2193 |
+
"step": 288
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.16,
|
| 2197 |
+
"learning_rate": 0.00014742268041237114,
|
| 2198 |
+
"loss": 0.3408,
|
| 2199 |
+
"step": 289
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.16,
|
| 2203 |
+
"learning_rate": 0.00014721649484536085,
|
| 2204 |
+
"loss": 0.2536,
|
| 2205 |
+
"step": 290
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 1.16,
|
| 2209 |
+
"eval_loss": 0.5906583070755005,
|
| 2210 |
+
"eval_runtime": 58.0348,
|
| 2211 |
+
"eval_samples_per_second": 4.308,
|
| 2212 |
+
"eval_steps_per_second": 0.551,
|
| 2213 |
+
"step": 290
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 1.16,
|
| 2217 |
+
"learning_rate": 0.00014701030927835053,
|
| 2218 |
+
"loss": 0.3943,
|
| 2219 |
+
"step": 291
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 1.17,
|
| 2223 |
+
"learning_rate": 0.0001468041237113402,
|
| 2224 |
+
"loss": 0.3739,
|
| 2225 |
+
"step": 292
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 1.17,
|
| 2229 |
+
"learning_rate": 0.0001465979381443299,
|
| 2230 |
+
"loss": 0.405,
|
| 2231 |
+
"step": 293
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 1.18,
|
| 2235 |
+
"learning_rate": 0.00014639175257731958,
|
| 2236 |
+
"loss": 0.3548,
|
| 2237 |
+
"step": 294
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.18,
|
| 2241 |
+
"learning_rate": 0.00014618556701030927,
|
| 2242 |
+
"loss": 0.462,
|
| 2243 |
+
"step": 295
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.18,
|
| 2247 |
+
"eval_loss": 0.6061128973960876,
|
| 2248 |
+
"eval_runtime": 57.9993,
|
| 2249 |
+
"eval_samples_per_second": 4.31,
|
| 2250 |
+
"eval_steps_per_second": 0.552,
|
| 2251 |
+
"step": 295
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 1.18,
|
| 2255 |
+
"learning_rate": 0.00014597938144329898,
|
| 2256 |
+
"loss": 0.3555,
|
| 2257 |
+
"step": 296
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.19,
|
| 2261 |
+
"learning_rate": 0.00014577319587628866,
|
| 2262 |
+
"loss": 0.414,
|
| 2263 |
+
"step": 297
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.19,
|
| 2267 |
+
"learning_rate": 0.00014556701030927834,
|
| 2268 |
+
"loss": 0.2916,
|
| 2269 |
+
"step": 298
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 1.2,
|
| 2273 |
+
"learning_rate": 0.00014536082474226805,
|
| 2274 |
+
"loss": 0.2507,
|
| 2275 |
+
"step": 299
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 1.2,
|
| 2279 |
+
"learning_rate": 0.00014515463917525774,
|
| 2280 |
+
"loss": 0.3295,
|
| 2281 |
+
"step": 300
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 1.2,
|
| 2285 |
+
"eval_loss": 0.6123625636100769,
|
| 2286 |
+
"eval_runtime": 57.7714,
|
| 2287 |
+
"eval_samples_per_second": 4.327,
|
| 2288 |
+
"eval_steps_per_second": 0.554,
|
| 2289 |
+
"step": 300
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 1.2,
|
| 2293 |
+
"learning_rate": 0.00014494845360824742,
|
| 2294 |
+
"loss": 0.5293,
|
| 2295 |
+
"step": 301
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 1.21,
|
| 2299 |
+
"learning_rate": 0.0001447422680412371,
|
| 2300 |
+
"loss": 0.686,
|
| 2301 |
+
"step": 302
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 1.21,
|
| 2305 |
+
"learning_rate": 0.00014453608247422682,
|
| 2306 |
+
"loss": 0.4869,
|
| 2307 |
+
"step": 303
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 1.22,
|
| 2311 |
+
"learning_rate": 0.0001443298969072165,
|
| 2312 |
+
"loss": 0.5161,
|
| 2313 |
+
"step": 304
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.22,
|
| 2317 |
+
"learning_rate": 0.00014412371134020618,
|
| 2318 |
+
"loss": 0.4381,
|
| 2319 |
+
"step": 305
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.22,
|
| 2323 |
+
"eval_loss": 0.576439619064331,
|
| 2324 |
+
"eval_runtime": 58.162,
|
| 2325 |
+
"eval_samples_per_second": 4.298,
|
| 2326 |
+
"eval_steps_per_second": 0.55,
|
| 2327 |
+
"step": 305
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.22,
|
| 2331 |
+
"learning_rate": 0.0001439175257731959,
|
| 2332 |
+
"loss": 0.5365,
|
| 2333 |
+
"step": 306
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.23,
|
| 2337 |
+
"learning_rate": 0.00014371134020618558,
|
| 2338 |
+
"loss": 0.4769,
|
| 2339 |
+
"step": 307
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 1.23,
|
| 2343 |
+
"learning_rate": 0.00014350515463917526,
|
| 2344 |
+
"loss": 0.555,
|
| 2345 |
+
"step": 308
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 1.24,
|
| 2349 |
+
"learning_rate": 0.00014329896907216494,
|
| 2350 |
+
"loss": 0.5363,
|
| 2351 |
+
"step": 309
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 1.24,
|
| 2355 |
+
"learning_rate": 0.00014309278350515465,
|
| 2356 |
+
"loss": 0.5696,
|
| 2357 |
+
"step": 310
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 1.24,
|
| 2361 |
+
"eval_loss": 0.5902033448219299,
|
| 2362 |
+
"eval_runtime": 58.1218,
|
| 2363 |
+
"eval_samples_per_second": 4.301,
|
| 2364 |
+
"eval_steps_per_second": 0.551,
|
| 2365 |
+
"step": 310
|
| 2366 |
+
},
|
| 2367 |
+
{
|
| 2368 |
+
"epoch": 1.24,
|
| 2369 |
+
"learning_rate": 0.00014288659793814434,
|
| 2370 |
+
"loss": 0.5701,
|
| 2371 |
+
"step": 311
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 1.25,
|
| 2375 |
+
"learning_rate": 0.00014268041237113402,
|
| 2376 |
+
"loss": 0.4742,
|
| 2377 |
+
"step": 312
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 1.25,
|
| 2381 |
+
"learning_rate": 0.00014247422680412373,
|
| 2382 |
+
"loss": 0.5453,
|
| 2383 |
+
"step": 313
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.26,
|
| 2387 |
+
"learning_rate": 0.00014226804123711342,
|
| 2388 |
+
"loss": 0.4795,
|
| 2389 |
+
"step": 314
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.26,
|
| 2393 |
+
"learning_rate": 0.0001420618556701031,
|
| 2394 |
+
"loss": 0.4853,
|
| 2395 |
+
"step": 315
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 1.26,
|
| 2399 |
+
"eval_loss": 0.575286865234375,
|
| 2400 |
+
"eval_runtime": 57.7708,
|
| 2401 |
+
"eval_samples_per_second": 4.327,
|
| 2402 |
+
"eval_steps_per_second": 0.554,
|
| 2403 |
+
"step": 315
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.26,
|
| 2407 |
+
"learning_rate": 0.0001418556701030928,
|
| 2408 |
+
"loss": 0.4996,
|
| 2409 |
+
"step": 316
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 1.27,
|
| 2413 |
+
"learning_rate": 0.0001416494845360825,
|
| 2414 |
+
"loss": 0.3985,
|
| 2415 |
+
"step": 317
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 1.27,
|
| 2419 |
+
"learning_rate": 0.00014144329896907218,
|
| 2420 |
+
"loss": 0.4474,
|
| 2421 |
+
"step": 318
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 1.28,
|
| 2425 |
+
"learning_rate": 0.00014123711340206186,
|
| 2426 |
+
"loss": 0.5442,
|
| 2427 |
+
"step": 319
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 1.28,
|
| 2431 |
+
"learning_rate": 0.00014103092783505157,
|
| 2432 |
+
"loss": 0.5395,
|
| 2433 |
+
"step": 320
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 1.28,
|
| 2437 |
+
"eval_loss": 0.5742917656898499,
|
| 2438 |
+
"eval_runtime": 57.9054,
|
| 2439 |
+
"eval_samples_per_second": 4.317,
|
| 2440 |
+
"eval_steps_per_second": 0.553,
|
| 2441 |
+
"step": 320
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 1.28,
|
| 2445 |
+
"learning_rate": 0.00014082474226804125,
|
| 2446 |
+
"loss": 0.4698,
|
| 2447 |
+
"step": 321
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 1.29,
|
| 2451 |
+
"learning_rate": 0.0001406185567010309,
|
| 2452 |
+
"loss": 0.5232,
|
| 2453 |
+
"step": 322
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.29,
|
| 2457 |
+
"learning_rate": 0.00014041237113402062,
|
| 2458 |
+
"loss": 0.41,
|
| 2459 |
+
"step": 323
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.3,
|
| 2463 |
+
"learning_rate": 0.0001402061855670103,
|
| 2464 |
+
"loss": 0.4899,
|
| 2465 |
+
"step": 324
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 1.3,
|
| 2469 |
+
"learning_rate": 0.00014,
|
| 2470 |
+
"loss": 0.4355,
|
| 2471 |
+
"step": 325
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 1.3,
|
| 2475 |
+
"eval_loss": 0.5757585763931274,
|
| 2476 |
+
"eval_runtime": 58.18,
|
| 2477 |
+
"eval_samples_per_second": 4.297,
|
| 2478 |
+
"eval_steps_per_second": 0.55,
|
| 2479 |
+
"step": 325
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 1.3,
|
| 2483 |
+
"learning_rate": 0.0001397938144329897,
|
| 2484 |
+
"loss": 0.4128,
|
| 2485 |
+
"step": 326
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 1.31,
|
| 2489 |
+
"learning_rate": 0.00013958762886597938,
|
| 2490 |
+
"loss": 0.4048,
|
| 2491 |
+
"step": 327
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 1.31,
|
| 2495 |
+
"learning_rate": 0.00013938144329896907,
|
| 2496 |
+
"loss": 0.4656,
|
| 2497 |
+
"step": 328
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 1.32,
|
| 2501 |
+
"learning_rate": 0.00013917525773195878,
|
| 2502 |
+
"loss": 0.3682,
|
| 2503 |
+
"step": 329
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 1.32,
|
| 2507 |
+
"learning_rate": 0.00013896907216494846,
|
| 2508 |
+
"loss": 0.4943,
|
| 2509 |
+
"step": 330
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.32,
|
| 2513 |
+
"eval_loss": 0.5842174291610718,
|
| 2514 |
+
"eval_runtime": 57.8497,
|
| 2515 |
+
"eval_samples_per_second": 4.322,
|
| 2516 |
+
"eval_steps_per_second": 0.553,
|
| 2517 |
+
"step": 330
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 1.32,
|
| 2521 |
+
"learning_rate": 0.00013876288659793814,
|
| 2522 |
+
"loss": 0.3817,
|
| 2523 |
+
"step": 331
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.33,
|
| 2527 |
+
"learning_rate": 0.00013855670103092783,
|
| 2528 |
+
"loss": 0.4528,
|
| 2529 |
+
"step": 332
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.33,
|
| 2533 |
+
"learning_rate": 0.00013835051546391754,
|
| 2534 |
+
"loss": 0.3355,
|
| 2535 |
+
"step": 333
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 1.34,
|
| 2539 |
+
"learning_rate": 0.00013814432989690722,
|
| 2540 |
+
"loss": 0.4085,
|
| 2541 |
+
"step": 334
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 1.34,
|
| 2545 |
+
"learning_rate": 0.0001379381443298969,
|
| 2546 |
+
"loss": 0.3934,
|
| 2547 |
+
"step": 335
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 1.34,
|
| 2551 |
+
"eval_loss": 0.5792785882949829,
|
| 2552 |
+
"eval_runtime": 58.0391,
|
| 2553 |
+
"eval_samples_per_second": 4.307,
|
| 2554 |
+
"eval_steps_per_second": 0.551,
|
| 2555 |
+
"step": 335
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 1.34,
|
| 2559 |
+
"learning_rate": 0.00013773195876288661,
|
| 2560 |
+
"loss": 0.3289,
|
| 2561 |
+
"step": 336
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 1.35,
|
| 2565 |
+
"learning_rate": 0.0001375257731958763,
|
| 2566 |
+
"loss": 0.3551,
|
| 2567 |
+
"step": 337
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 1.35,
|
| 2571 |
+
"learning_rate": 0.00013731958762886598,
|
| 2572 |
+
"loss": 0.3062,
|
| 2573 |
+
"step": 338
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 1.36,
|
| 2577 |
+
"learning_rate": 0.00013711340206185566,
|
| 2578 |
+
"loss": 0.3588,
|
| 2579 |
+
"step": 339
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.36,
|
| 2583 |
+
"learning_rate": 0.00013690721649484538,
|
| 2584 |
+
"loss": 0.2947,
|
| 2585 |
+
"step": 340
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 1.36,
|
| 2589 |
+
"eval_loss": 0.5880213975906372,
|
| 2590 |
+
"eval_runtime": 58.0627,
|
| 2591 |
+
"eval_samples_per_second": 4.306,
|
| 2592 |
+
"eval_steps_per_second": 0.551,
|
| 2593 |
+
"step": 340
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.36,
|
| 2597 |
+
"learning_rate": 0.00013670103092783506,
|
| 2598 |
+
"loss": 0.4527,
|
| 2599 |
+
"step": 341
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 1.37,
|
| 2603 |
+
"learning_rate": 0.00013649484536082474,
|
| 2604 |
+
"loss": 0.413,
|
| 2605 |
+
"step": 342
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 1.37,
|
| 2609 |
+
"learning_rate": 0.00013628865979381445,
|
| 2610 |
+
"loss": 0.3439,
|
| 2611 |
+
"step": 343
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 1.38,
|
| 2615 |
+
"learning_rate": 0.00013608247422680414,
|
| 2616 |
+
"loss": 0.3529,
|
| 2617 |
+
"step": 344
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 1.38,
|
| 2621 |
+
"learning_rate": 0.00013587628865979382,
|
| 2622 |
+
"loss": 0.3427,
|
| 2623 |
+
"step": 345
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 1.38,
|
| 2627 |
+
"eval_loss": 0.5902564525604248,
|
| 2628 |
+
"eval_runtime": 58.0661,
|
| 2629 |
+
"eval_samples_per_second": 4.305,
|
| 2630 |
+
"eval_steps_per_second": 0.551,
|
| 2631 |
+
"step": 345
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 1.38,
|
| 2635 |
+
"learning_rate": 0.00013567010309278353,
|
| 2636 |
+
"loss": 0.3917,
|
| 2637 |
+
"step": 346
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 1.39,
|
| 2641 |
+
"learning_rate": 0.00013546391752577321,
|
| 2642 |
+
"loss": 0.2853,
|
| 2643 |
+
"step": 347
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 1.39,
|
| 2647 |
+
"learning_rate": 0.0001352577319587629,
|
| 2648 |
+
"loss": 0.2518,
|
| 2649 |
+
"step": 348
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.4,
|
| 2653 |
+
"learning_rate": 0.00013505154639175258,
|
| 2654 |
+
"loss": 0.3215,
|
| 2655 |
+
"step": 349
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 1.4,
|
| 2659 |
+
"learning_rate": 0.0001348453608247423,
|
| 2660 |
+
"loss": 0.2906,
|
| 2661 |
+
"step": 350
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 1.4,
|
| 2665 |
+
"eval_loss": 0.6013336181640625,
|
| 2666 |
+
"eval_runtime": 58.0155,
|
| 2667 |
+
"eval_samples_per_second": 4.309,
|
| 2668 |
+
"eval_steps_per_second": 0.552,
|
| 2669 |
+
"step": 350
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 1.4,
|
| 2673 |
+
"learning_rate": 0.00013463917525773197,
|
| 2674 |
+
"loss": 0.6485,
|
| 2675 |
+
"step": 351
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 1.41,
|
| 2679 |
+
"learning_rate": 0.00013443298969072166,
|
| 2680 |
+
"loss": 0.6829,
|
| 2681 |
+
"step": 352
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"epoch": 1.41,
|
| 2685 |
+
"learning_rate": 0.00013422680412371134,
|
| 2686 |
+
"loss": 0.5409,
|
| 2687 |
+
"step": 353
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 1.42,
|
| 2691 |
+
"learning_rate": 0.00013402061855670103,
|
| 2692 |
+
"loss": 0.7209,
|
| 2693 |
+
"step": 354
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 1.42,
|
| 2697 |
+
"learning_rate": 0.0001338144329896907,
|
| 2698 |
+
"loss": 0.5774,
|
| 2699 |
+
"step": 355
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 1.42,
|
| 2703 |
+
"eval_loss": 0.583857536315918,
|
| 2704 |
+
"eval_runtime": 57.8931,
|
| 2705 |
+
"eval_samples_per_second": 4.318,
|
| 2706 |
+
"eval_steps_per_second": 0.553,
|
| 2707 |
+
"step": 355
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 1.42,
|
| 2711 |
+
"learning_rate": 0.00013360824742268042,
|
| 2712 |
+
"loss": 0.5123,
|
| 2713 |
+
"step": 356
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 1.43,
|
| 2717 |
+
"learning_rate": 0.0001334020618556701,
|
| 2718 |
+
"loss": 0.6287,
|
| 2719 |
+
"step": 357
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.43,
|
| 2723 |
+
"learning_rate": 0.00013319587628865979,
|
| 2724 |
+
"loss": 0.641,
|
| 2725 |
+
"step": 358
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 1.44,
|
| 2729 |
+
"learning_rate": 0.0001329896907216495,
|
| 2730 |
+
"loss": 0.5998,
|
| 2731 |
+
"step": 359
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 1.44,
|
| 2735 |
+
"learning_rate": 0.00013278350515463918,
|
| 2736 |
+
"loss": 0.4529,
|
| 2737 |
+
"step": 360
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 1.44,
|
| 2741 |
+
"eval_loss": 0.581903338432312,
|
| 2742 |
+
"eval_runtime": 57.8521,
|
| 2743 |
+
"eval_samples_per_second": 4.321,
|
| 2744 |
+
"eval_steps_per_second": 0.553,
|
| 2745 |
+
"step": 360
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 1.44,
|
| 2749 |
+
"learning_rate": 0.00013257731958762886,
|
| 2750 |
+
"loss": 0.4551,
|
| 2751 |
+
"step": 361
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 1.45,
|
| 2755 |
+
"learning_rate": 0.00013237113402061855,
|
| 2756 |
+
"loss": 0.4757,
|
| 2757 |
+
"step": 362
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 1.45,
|
| 2761 |
+
"learning_rate": 0.00013216494845360826,
|
| 2762 |
+
"loss": 0.4402,
|
| 2763 |
+
"step": 363
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 1.46,
|
| 2767 |
+
"learning_rate": 0.00013195876288659794,
|
| 2768 |
+
"loss": 0.4174,
|
| 2769 |
+
"step": 364
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 1.46,
|
| 2773 |
+
"learning_rate": 0.00013175257731958762,
|
| 2774 |
+
"loss": 0.4431,
|
| 2775 |
+
"step": 365
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.46,
|
| 2779 |
+
"eval_loss": 0.5788648128509521,
|
| 2780 |
+
"eval_runtime": 58.1681,
|
| 2781 |
+
"eval_samples_per_second": 4.298,
|
| 2782 |
+
"eval_steps_per_second": 0.55,
|
| 2783 |
+
"step": 365
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 1.46,
|
| 2787 |
+
"learning_rate": 0.00013154639175257734,
|
| 2788 |
+
"loss": 0.4286,
|
| 2789 |
+
"step": 366
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.47,
|
| 2793 |
+
"learning_rate": 0.00013134020618556702,
|
| 2794 |
+
"loss": 0.4597,
|
| 2795 |
+
"step": 367
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 1.47,
|
| 2799 |
+
"learning_rate": 0.0001311340206185567,
|
| 2800 |
+
"loss": 0.5148,
|
| 2801 |
+
"step": 368
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 1.48,
|
| 2805 |
+
"learning_rate": 0.00013092783505154639,
|
| 2806 |
+
"loss": 0.5256,
|
| 2807 |
+
"step": 369
|
| 2808 |
+
},
|
| 2809 |
+
{
|
| 2810 |
+
"epoch": 1.48,
|
| 2811 |
+
"learning_rate": 0.0001307216494845361,
|
| 2812 |
+
"loss": 0.3836,
|
| 2813 |
+
"step": 370
|
| 2814 |
+
},
|
| 2815 |
+
{
|
| 2816 |
+
"epoch": 1.48,
|
| 2817 |
+
"eval_loss": 0.5807417035102844,
|
| 2818 |
+
"eval_runtime": 57.7395,
|
| 2819 |
+
"eval_samples_per_second": 4.33,
|
| 2820 |
+
"eval_steps_per_second": 0.554,
|
| 2821 |
+
"step": 370
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 1.48,
|
| 2825 |
+
"learning_rate": 0.00013051546391752578,
|
| 2826 |
+
"loss": 0.403,
|
| 2827 |
+
"step": 371
|
| 2828 |
+
},
|
| 2829 |
+
{
|
| 2830 |
+
"epoch": 1.49,
|
| 2831 |
+
"learning_rate": 0.00013030927835051546,
|
| 2832 |
+
"loss": 0.4942,
|
| 2833 |
+
"step": 372
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 1.49,
|
| 2837 |
+
"learning_rate": 0.00013010309278350517,
|
| 2838 |
+
"loss": 0.411,
|
| 2839 |
+
"step": 373
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 1.5,
|
| 2843 |
+
"learning_rate": 0.00012989690721649486,
|
| 2844 |
+
"loss": 0.4153,
|
| 2845 |
+
"step": 374
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 1.5,
|
| 2849 |
+
"learning_rate": 0.00012969072164948454,
|
| 2850 |
+
"loss": 0.4054,
|
| 2851 |
+
"step": 375
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 1.5,
|
| 2855 |
+
"eval_loss": 0.5868126153945923,
|
| 2856 |
+
"eval_runtime": 57.7457,
|
| 2857 |
+
"eval_samples_per_second": 4.329,
|
| 2858 |
+
"eval_steps_per_second": 0.554,
|
| 2859 |
+
"step": 375
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.5,
|
| 2863 |
+
"learning_rate": 0.00012948453608247425,
|
| 2864 |
+
"loss": 0.4248,
|
| 2865 |
+
"step": 376
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 1.51,
|
| 2869 |
+
"learning_rate": 0.00012927835051546393,
|
| 2870 |
+
"loss": 0.4231,
|
| 2871 |
+
"step": 377
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 1.51,
|
| 2875 |
+
"learning_rate": 0.00012907216494845362,
|
| 2876 |
+
"loss": 0.422,
|
| 2877 |
+
"step": 378
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 1.52,
|
| 2881 |
+
"learning_rate": 0.0001288659793814433,
|
| 2882 |
+
"loss": 0.3957,
|
| 2883 |
+
"step": 379
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 1.52,
|
| 2887 |
+
"learning_rate": 0.000128659793814433,
|
| 2888 |
+
"loss": 0.4463,
|
| 2889 |
+
"step": 380
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 1.52,
|
| 2893 |
+
"eval_loss": 0.5862159132957458,
|
| 2894 |
+
"eval_runtime": 58.2762,
|
| 2895 |
+
"eval_samples_per_second": 4.29,
|
| 2896 |
+
"eval_steps_per_second": 0.549,
|
| 2897 |
+
"step": 380
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 1.52,
|
| 2901 |
+
"learning_rate": 0.0001284536082474227,
|
| 2902 |
+
"loss": 0.4907,
|
| 2903 |
+
"step": 381
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 1.53,
|
| 2907 |
+
"learning_rate": 0.00012824742268041238,
|
| 2908 |
+
"loss": 0.4444,
|
| 2909 |
+
"step": 382
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 1.53,
|
| 2913 |
+
"learning_rate": 0.00012804123711340206,
|
| 2914 |
+
"loss": 0.4767,
|
| 2915 |
+
"step": 383
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 1.54,
|
| 2919 |
+
"learning_rate": 0.00012783505154639175,
|
| 2920 |
+
"loss": 0.4122,
|
| 2921 |
+
"step": 384
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 1.54,
|
| 2925 |
+
"learning_rate": 0.00012762886597938143,
|
| 2926 |
+
"loss": 0.4023,
|
| 2927 |
+
"step": 385
|
| 2928 |
+
},
|
| 2929 |
+
{
|
| 2930 |
+
"epoch": 1.54,
|
| 2931 |
+
"eval_loss": 0.582167387008667,
|
| 2932 |
+
"eval_runtime": 58.0372,
|
| 2933 |
+
"eval_samples_per_second": 4.308,
|
| 2934 |
+
"eval_steps_per_second": 0.551,
|
| 2935 |
+
"step": 385
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 1.54,
|
| 2939 |
+
"learning_rate": 0.00012742268041237114,
|
| 2940 |
+
"loss": 0.4174,
|
| 2941 |
+
"step": 386
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 1.55,
|
| 2945 |
+
"learning_rate": 0.00012721649484536082,
|
| 2946 |
+
"loss": 0.3888,
|
| 2947 |
+
"step": 387
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"epoch": 1.55,
|
| 2951 |
+
"learning_rate": 0.0001270103092783505,
|
| 2952 |
+
"loss": 0.2883,
|
| 2953 |
+
"step": 388
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 1.56,
|
| 2957 |
+
"learning_rate": 0.00012680412371134022,
|
| 2958 |
+
"loss": 0.4039,
|
| 2959 |
+
"step": 389
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 1.56,
|
| 2963 |
+
"learning_rate": 0.0001265979381443299,
|
| 2964 |
+
"loss": 0.3211,
|
| 2965 |
+
"step": 390
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 1.56,
|
| 2969 |
+
"eval_loss": 0.5785840749740601,
|
| 2970 |
+
"eval_runtime": 58.0313,
|
| 2971 |
+
"eval_samples_per_second": 4.308,
|
| 2972 |
+
"eval_steps_per_second": 0.551,
|
| 2973 |
+
"step": 390
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 1.56,
|
| 2977 |
+
"learning_rate": 0.00012639175257731958,
|
| 2978 |
+
"loss": 0.3414,
|
| 2979 |
+
"step": 391
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 1.57,
|
| 2983 |
+
"learning_rate": 0.00012618556701030927,
|
| 2984 |
+
"loss": 0.3639,
|
| 2985 |
+
"step": 392
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 1.57,
|
| 2989 |
+
"learning_rate": 0.00012597938144329898,
|
| 2990 |
+
"loss": 0.3687,
|
| 2991 |
+
"step": 393
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 1.58,
|
| 2995 |
+
"learning_rate": 0.00012577319587628866,
|
| 2996 |
+
"loss": 0.2935,
|
| 2997 |
+
"step": 394
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 1.58,
|
| 3001 |
+
"learning_rate": 0.00012556701030927835,
|
| 3002 |
+
"loss": 0.4914,
|
| 3003 |
+
"step": 395
|
| 3004 |
+
},
|
| 3005 |
+
{
|
| 3006 |
+
"epoch": 1.58,
|
| 3007 |
+
"eval_loss": 0.5804648399353027,
|
| 3008 |
+
"eval_runtime": 57.7946,
|
| 3009 |
+
"eval_samples_per_second": 4.326,
|
| 3010 |
+
"eval_steps_per_second": 0.554,
|
| 3011 |
+
"step": 395
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 1.58,
|
| 3015 |
+
"learning_rate": 0.00012536082474226806,
|
| 3016 |
+
"loss": 0.302,
|
| 3017 |
+
"step": 396
|
| 3018 |
+
},
|
| 3019 |
+
{
|
| 3020 |
+
"epoch": 1.59,
|
| 3021 |
+
"learning_rate": 0.00012515463917525774,
|
| 3022 |
+
"loss": 0.2966,
|
| 3023 |
+
"step": 397
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 1.59,
|
| 3027 |
+
"learning_rate": 0.00012494845360824742,
|
| 3028 |
+
"loss": 0.3726,
|
| 3029 |
+
"step": 398
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 1.6,
|
| 3033 |
+
"learning_rate": 0.0001247422680412371,
|
| 3034 |
+
"loss": 0.3031,
|
| 3035 |
+
"step": 399
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 1.6,
|
| 3039 |
+
"learning_rate": 0.00012453608247422682,
|
| 3040 |
+
"loss": 0.3497,
|
| 3041 |
+
"step": 400
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 1.6,
|
| 3045 |
+
"eval_loss": 0.5969975590705872,
|
| 3046 |
+
"eval_runtime": 58.0419,
|
| 3047 |
+
"eval_samples_per_second": 4.307,
|
| 3048 |
+
"eval_steps_per_second": 0.551,
|
| 3049 |
+
"step": 400
|
| 3050 |
}
|
| 3051 |
],
|
| 3052 |
"logging_steps": 1,
|
| 3053 |
+
"max_steps": 1000,
|
| 3054 |
+
"num_train_epochs": 4,
|
| 3055 |
"save_steps": 200,
|
| 3056 |
+
"total_flos": 9123743473139712.0,
|
| 3057 |
"trial_name": null,
|
| 3058 |
"trial_params": null
|
| 3059 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e3449204de7ba86a1e89188686e405bb45465e9138957adaef9caeb8c0640b6
|
| 3 |
size 4664
|