Upload 10 files
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +1485 -3
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598635032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cf6fd855c268d3938b4c6d6a77aa9284b5bd03c679875c89cb3579c489295b8
|
| 3 |
size 598635032
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1197359627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20d57d69e8d4eb0bcf9143bb2a5722964a200d83b3b1c090ed18f98299556b3a
|
| 3 |
size 1197359627
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be293c0bc96c40007a1ca95bf99da704f29c24d932c7c8e19b962a361adfdc4c
|
| 3 |
size 14645
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af5ee4dc438217ac40b2a125900214146b721f2725ba954be785ed61a3abe011
|
| 3 |
size 1465
|
trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -13041,6 +13041,1488 @@
|
|
| 13041 |
"eval_samples_per_second": 195.51,
|
| 13042 |
"eval_steps_per_second": 1.534,
|
| 13043 |
"step": 167000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13044 |
}
|
| 13045 |
],
|
| 13046 |
"logging_steps": 100,
|
|
@@ -13060,7 +14542,7 @@
|
|
| 13060 |
"attributes": {}
|
| 13061 |
}
|
| 13062 |
},
|
| 13063 |
-
"total_flos": 1.
|
| 13064 |
"train_batch_size": 128,
|
| 13065 |
"trial_name": null,
|
| 13066 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0055816341908584,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 186000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13041 |
"eval_samples_per_second": 195.51,
|
| 13042 |
"eval_steps_per_second": 1.534,
|
| 13043 |
"step": 167000
|
| 13044 |
+
},
|
| 13045 |
+
{
|
| 13046 |
+
"epoch": 0.01981480137754732,
|
| 13047 |
+
"grad_norm": 1.5712428092956543,
|
| 13048 |
+
"learning_rate": 2.8278830871985708e-05,
|
| 13049 |
+
"loss": 1.7747,
|
| 13050 |
+
"step": 167100
|
| 13051 |
+
},
|
| 13052 |
+
{
|
| 13053 |
+
"epoch": 0.020093883087090238,
|
| 13054 |
+
"grad_norm": 1.5386340618133545,
|
| 13055 |
+
"learning_rate": 2.8256880354422098e-05,
|
| 13056 |
+
"loss": 1.7738,
|
| 13057 |
+
"step": 167200
|
| 13058 |
+
},
|
| 13059 |
+
{
|
| 13060 |
+
"epoch": 0.02037296479663316,
|
| 13061 |
+
"grad_norm": 1.5471428632736206,
|
| 13062 |
+
"learning_rate": 2.8234927282417417e-05,
|
| 13063 |
+
"loss": 1.779,
|
| 13064 |
+
"step": 167300
|
| 13065 |
+
},
|
| 13066 |
+
{
|
| 13067 |
+
"epoch": 0.020652046506176077,
|
| 13068 |
+
"grad_norm": 1.5163718461990356,
|
| 13069 |
+
"learning_rate": 2.821297167318992e-05,
|
| 13070 |
+
"loss": 1.7741,
|
| 13071 |
+
"step": 167400
|
| 13072 |
+
},
|
| 13073 |
+
{
|
| 13074 |
+
"epoch": 0.020931128215719,
|
| 13075 |
+
"grad_norm": 1.5554001331329346,
|
| 13076 |
+
"learning_rate": 2.819101354395986e-05,
|
| 13077 |
+
"loss": 1.7825,
|
| 13078 |
+
"step": 167500
|
| 13079 |
+
},
|
| 13080 |
+
{
|
| 13081 |
+
"epoch": 0.02121020992526192,
|
| 13082 |
+
"grad_norm": 1.4839155673980713,
|
| 13083 |
+
"learning_rate": 2.8169052911949484e-05,
|
| 13084 |
+
"loss": 1.7729,
|
| 13085 |
+
"step": 167600
|
| 13086 |
+
},
|
| 13087 |
+
{
|
| 13088 |
+
"epoch": 0.021489291634804838,
|
| 13089 |
+
"grad_norm": 1.5696512460708618,
|
| 13090 |
+
"learning_rate": 2.8147089794382965e-05,
|
| 13091 |
+
"loss": 1.7754,
|
| 13092 |
+
"step": 167700
|
| 13093 |
+
},
|
| 13094 |
+
{
|
| 13095 |
+
"epoch": 0.02176837334434776,
|
| 13096 |
+
"grad_norm": 1.6730250120162964,
|
| 13097 |
+
"learning_rate": 2.8125124208486465e-05,
|
| 13098 |
+
"loss": 1.7736,
|
| 13099 |
+
"step": 167800
|
| 13100 |
+
},
|
| 13101 |
+
{
|
| 13102 |
+
"epoch": 0.022047455053890677,
|
| 13103 |
+
"grad_norm": 1.6201075315475464,
|
| 13104 |
+
"learning_rate": 2.810315617148806e-05,
|
| 13105 |
+
"loss": 1.7771,
|
| 13106 |
+
"step": 167900
|
| 13107 |
+
},
|
| 13108 |
+
{
|
| 13109 |
+
"epoch": 0.0223265367634336,
|
| 13110 |
+
"grad_norm": 1.6662862300872803,
|
| 13111 |
+
"learning_rate": 2.8081185700617746e-05,
|
| 13112 |
+
"loss": 1.7761,
|
| 13113 |
+
"step": 168000
|
| 13114 |
+
},
|
| 13115 |
+
{
|
| 13116 |
+
"epoch": 0.0223265367634336,
|
| 13117 |
+
"eval_loss": 2.161256790161133,
|
| 13118 |
+
"eval_runtime": 52.0964,
|
| 13119 |
+
"eval_samples_per_second": 195.676,
|
| 13120 |
+
"eval_steps_per_second": 1.536,
|
| 13121 |
+
"step": 168000
|
| 13122 |
+
},
|
| 13123 |
+
{
|
| 13124 |
+
"epoch": 0.022605618472976517,
|
| 13125 |
+
"grad_norm": 1.4697953462600708,
|
| 13126 |
+
"learning_rate": 2.8059212813107438e-05,
|
| 13127 |
+
"loss": 1.7894,
|
| 13128 |
+
"step": 168100
|
| 13129 |
+
},
|
| 13130 |
+
{
|
| 13131 |
+
"epoch": 0.022884700182519438,
|
| 13132 |
+
"grad_norm": 1.6400997638702393,
|
| 13133 |
+
"learning_rate": 2.803723752619094e-05,
|
| 13134 |
+
"loss": 1.7779,
|
| 13135 |
+
"step": 168200
|
| 13136 |
+
},
|
| 13137 |
+
{
|
| 13138 |
+
"epoch": 0.02316378189206236,
|
| 13139 |
+
"grad_norm": 1.5220052003860474,
|
| 13140 |
+
"learning_rate": 2.8015259857103942e-05,
|
| 13141 |
+
"loss": 1.7732,
|
| 13142 |
+
"step": 168300
|
| 13143 |
+
},
|
| 13144 |
+
{
|
| 13145 |
+
"epoch": 0.023442863601605277,
|
| 13146 |
+
"grad_norm": 1.542869210243225,
|
| 13147 |
+
"learning_rate": 2.7993279823084007e-05,
|
| 13148 |
+
"loss": 1.7771,
|
| 13149 |
+
"step": 168400
|
| 13150 |
+
},
|
| 13151 |
+
{
|
| 13152 |
+
"epoch": 0.0237219453111482,
|
| 13153 |
+
"grad_norm": 1.4953099489212036,
|
| 13154 |
+
"learning_rate": 2.7971297441370542e-05,
|
| 13155 |
+
"loss": 1.7774,
|
| 13156 |
+
"step": 168500
|
| 13157 |
+
},
|
| 13158 |
+
{
|
| 13159 |
+
"epoch": 0.024001027020691117,
|
| 13160 |
+
"grad_norm": 1.5665849447250366,
|
| 13161 |
+
"learning_rate": 2.7949312729204803e-05,
|
| 13162 |
+
"loss": 1.7633,
|
| 13163 |
+
"step": 168600
|
| 13164 |
+
},
|
| 13165 |
+
{
|
| 13166 |
+
"epoch": 0.024280108730234038,
|
| 13167 |
+
"grad_norm": 1.5860687494277954,
|
| 13168 |
+
"learning_rate": 2.792732570382986e-05,
|
| 13169 |
+
"loss": 1.7798,
|
| 13170 |
+
"step": 168700
|
| 13171 |
+
},
|
| 13172 |
+
{
|
| 13173 |
+
"epoch": 0.02455919043977696,
|
| 13174 |
+
"grad_norm": 1.602845311164856,
|
| 13175 |
+
"learning_rate": 2.790533638249062e-05,
|
| 13176 |
+
"loss": 1.7694,
|
| 13177 |
+
"step": 168800
|
| 13178 |
+
},
|
| 13179 |
+
{
|
| 13180 |
+
"epoch": 0.024838272149319877,
|
| 13181 |
+
"grad_norm": 1.5015400648117065,
|
| 13182 |
+
"learning_rate": 2.7883344782433774e-05,
|
| 13183 |
+
"loss": 1.7628,
|
| 13184 |
+
"step": 168900
|
| 13185 |
+
},
|
| 13186 |
+
{
|
| 13187 |
+
"epoch": 0.0251173538588628,
|
| 13188 |
+
"grad_norm": 1.5296344757080078,
|
| 13189 |
+
"learning_rate": 2.7861350920907807e-05,
|
| 13190 |
+
"loss": 1.7753,
|
| 13191 |
+
"step": 169000
|
| 13192 |
+
},
|
| 13193 |
+
{
|
| 13194 |
+
"epoch": 0.0251173538588628,
|
| 13195 |
+
"eval_loss": 2.1639742851257324,
|
| 13196 |
+
"eval_runtime": 52.1527,
|
| 13197 |
+
"eval_samples_per_second": 195.465,
|
| 13198 |
+
"eval_steps_per_second": 1.534,
|
| 13199 |
+
"step": 169000
|
| 13200 |
+
},
|
| 13201 |
+
{
|
| 13202 |
+
"epoch": 0.025396435568405717,
|
| 13203 |
+
"grad_norm": 1.591369390487671,
|
| 13204 |
+
"learning_rate": 2.783935481516297e-05,
|
| 13205 |
+
"loss": 1.7695,
|
| 13206 |
+
"step": 169100
|
| 13207 |
+
},
|
| 13208 |
+
{
|
| 13209 |
+
"epoch": 0.025675517277948638,
|
| 13210 |
+
"grad_norm": 1.5569419860839844,
|
| 13211 |
+
"learning_rate": 2.7817356482451297e-05,
|
| 13212 |
+
"loss": 1.7689,
|
| 13213 |
+
"step": 169200
|
| 13214 |
+
},
|
| 13215 |
+
{
|
| 13216 |
+
"epoch": 0.025954598987491556,
|
| 13217 |
+
"grad_norm": 1.6080352067947388,
|
| 13218 |
+
"learning_rate": 2.779535594002654e-05,
|
| 13219 |
+
"loss": 1.767,
|
| 13220 |
+
"step": 169300
|
| 13221 |
+
},
|
| 13222 |
+
{
|
| 13223 |
+
"epoch": 0.026233680697034478,
|
| 13224 |
+
"grad_norm": 1.47182035446167,
|
| 13225 |
+
"learning_rate": 2.77733532051442e-05,
|
| 13226 |
+
"loss": 1.7717,
|
| 13227 |
+
"step": 169400
|
| 13228 |
+
},
|
| 13229 |
+
{
|
| 13230 |
+
"epoch": 0.0265127624065774,
|
| 13231 |
+
"grad_norm": 1.6706403493881226,
|
| 13232 |
+
"learning_rate": 2.775134829506148e-05,
|
| 13233 |
+
"loss": 1.7787,
|
| 13234 |
+
"step": 169500
|
| 13235 |
+
},
|
| 13236 |
+
{
|
| 13237 |
+
"epoch": 0.026791844116120317,
|
| 13238 |
+
"grad_norm": 1.6530786752700806,
|
| 13239 |
+
"learning_rate": 2.7729341227037313e-05,
|
| 13240 |
+
"loss": 1.7726,
|
| 13241 |
+
"step": 169600
|
| 13242 |
+
},
|
| 13243 |
+
{
|
| 13244 |
+
"epoch": 0.02707092582566324,
|
| 13245 |
+
"grad_norm": 1.4457296133041382,
|
| 13246 |
+
"learning_rate": 2.7707332018332323e-05,
|
| 13247 |
+
"loss": 1.7697,
|
| 13248 |
+
"step": 169700
|
| 13249 |
+
},
|
| 13250 |
+
{
|
| 13251 |
+
"epoch": 0.027350007535206156,
|
| 13252 |
+
"grad_norm": 1.5824190378189087,
|
| 13253 |
+
"learning_rate": 2.7685320686208793e-05,
|
| 13254 |
+
"loss": 1.7734,
|
| 13255 |
+
"step": 169800
|
| 13256 |
+
},
|
| 13257 |
+
{
|
| 13258 |
+
"epoch": 0.027629089244749078,
|
| 13259 |
+
"grad_norm": 1.6177047491073608,
|
| 13260 |
+
"learning_rate": 2.7663307247930686e-05,
|
| 13261 |
+
"loss": 1.7782,
|
| 13262 |
+
"step": 169900
|
| 13263 |
+
},
|
| 13264 |
+
{
|
| 13265 |
+
"epoch": 0.027908170954292,
|
| 13266 |
+
"grad_norm": 1.505018949508667,
|
| 13267 |
+
"learning_rate": 2.7641291720763612e-05,
|
| 13268 |
+
"loss": 1.7659,
|
| 13269 |
+
"step": 170000
|
| 13270 |
+
},
|
| 13271 |
+
{
|
| 13272 |
+
"epoch": 0.027908170954292,
|
| 13273 |
+
"eval_loss": 2.1508195400238037,
|
| 13274 |
+
"eval_runtime": 52.1147,
|
| 13275 |
+
"eval_samples_per_second": 195.607,
|
| 13276 |
+
"eval_steps_per_second": 1.535,
|
| 13277 |
+
"step": 170000
|
| 13278 |
+
},
|
| 13279 |
+
{
|
| 13280 |
+
"epoch": 0.028187252663834917,
|
| 13281 |
+
"grad_norm": 1.6319383382797241,
|
| 13282 |
+
"learning_rate": 2.7619274121974825e-05,
|
| 13283 |
+
"loss": 1.7709,
|
| 13284 |
+
"step": 170100
|
| 13285 |
+
},
|
| 13286 |
+
{
|
| 13287 |
+
"epoch": 0.02846633437337784,
|
| 13288 |
+
"grad_norm": 1.6314260959625244,
|
| 13289 |
+
"learning_rate": 2.759725446883319e-05,
|
| 13290 |
+
"loss": 1.7675,
|
| 13291 |
+
"step": 170200
|
| 13292 |
+
},
|
| 13293 |
+
{
|
| 13294 |
+
"epoch": 0.028745416082920756,
|
| 13295 |
+
"grad_norm": 1.471872329711914,
|
| 13296 |
+
"learning_rate": 2.7575232778609206e-05,
|
| 13297 |
+
"loss": 1.771,
|
| 13298 |
+
"step": 170300
|
| 13299 |
+
},
|
| 13300 |
+
{
|
| 13301 |
+
"epoch": 0.029024497792463678,
|
| 13302 |
+
"grad_norm": 1.5450881719589233,
|
| 13303 |
+
"learning_rate": 2.755320906857494e-05,
|
| 13304 |
+
"loss": 1.836,
|
| 13305 |
+
"step": 170400
|
| 13306 |
+
},
|
| 13307 |
+
{
|
| 13308 |
+
"epoch": 0.0293035795020066,
|
| 13309 |
+
"grad_norm": 1.5527344942092896,
|
| 13310 |
+
"learning_rate": 2.753118335600408e-05,
|
| 13311 |
+
"loss": 1.8808,
|
| 13312 |
+
"step": 170500
|
| 13313 |
+
},
|
| 13314 |
+
{
|
| 13315 |
+
"epoch": 0.029582661211549517,
|
| 13316 |
+
"grad_norm": 1.8364976644515991,
|
| 13317 |
+
"learning_rate": 2.7509155658171852e-05,
|
| 13318 |
+
"loss": 1.8776,
|
| 13319 |
+
"step": 170600
|
| 13320 |
+
},
|
| 13321 |
+
{
|
| 13322 |
+
"epoch": 0.02986174292109244,
|
| 13323 |
+
"grad_norm": 1.4847674369812012,
|
| 13324 |
+
"learning_rate": 2.7487125992355058e-05,
|
| 13325 |
+
"loss": 1.8724,
|
| 13326 |
+
"step": 170700
|
| 13327 |
+
},
|
| 13328 |
+
{
|
| 13329 |
+
"epoch": 0.030140824630635357,
|
| 13330 |
+
"grad_norm": 1.5595808029174805,
|
| 13331 |
+
"learning_rate": 2.7465094375832028e-05,
|
| 13332 |
+
"loss": 1.8799,
|
| 13333 |
+
"step": 170800
|
| 13334 |
+
},
|
| 13335 |
+
{
|
| 13336 |
+
"epoch": 0.030419906340178278,
|
| 13337 |
+
"grad_norm": 1.54868483543396,
|
| 13338 |
+
"learning_rate": 2.744306082588264e-05,
|
| 13339 |
+
"loss": 1.8704,
|
| 13340 |
+
"step": 170900
|
| 13341 |
+
},
|
| 13342 |
+
{
|
| 13343 |
+
"epoch": 0.030698988049721196,
|
| 13344 |
+
"grad_norm": 1.8504784107208252,
|
| 13345 |
+
"learning_rate": 2.742102535978827e-05,
|
| 13346 |
+
"loss": 1.8736,
|
| 13347 |
+
"step": 171000
|
| 13348 |
+
},
|
| 13349 |
+
{
|
| 13350 |
+
"epoch": 0.030698988049721196,
|
| 13351 |
+
"eval_loss": 2.1541635990142822,
|
| 13352 |
+
"eval_runtime": 52.1803,
|
| 13353 |
+
"eval_samples_per_second": 195.361,
|
| 13354 |
+
"eval_steps_per_second": 1.533,
|
| 13355 |
+
"step": 171000
|
| 13356 |
+
},
|
| 13357 |
+
{
|
| 13358 |
+
"epoch": 0.030978069759264117,
|
| 13359 |
+
"grad_norm": 1.6168150901794434,
|
| 13360 |
+
"learning_rate": 2.7398987994831822e-05,
|
| 13361 |
+
"loss": 1.8737,
|
| 13362 |
+
"step": 171100
|
| 13363 |
+
},
|
| 13364 |
+
{
|
| 13365 |
+
"epoch": 0.03125715146880704,
|
| 13366 |
+
"grad_norm": 1.6291587352752686,
|
| 13367 |
+
"learning_rate": 2.737694874829766e-05,
|
| 13368 |
+
"loss": 1.8691,
|
| 13369 |
+
"step": 171200
|
| 13370 |
+
},
|
| 13371 |
+
{
|
| 13372 |
+
"epoch": 0.03153623317834996,
|
| 13373 |
+
"grad_norm": 1.5887749195098877,
|
| 13374 |
+
"learning_rate": 2.735490763747164e-05,
|
| 13375 |
+
"loss": 1.8725,
|
| 13376 |
+
"step": 171300
|
| 13377 |
+
},
|
| 13378 |
+
{
|
| 13379 |
+
"epoch": 0.031815314887892875,
|
| 13380 |
+
"grad_norm": 1.6395853757858276,
|
| 13381 |
+
"learning_rate": 2.733286467964108e-05,
|
| 13382 |
+
"loss": 1.8857,
|
| 13383 |
+
"step": 171400
|
| 13384 |
+
},
|
| 13385 |
+
{
|
| 13386 |
+
"epoch": 0.0320943965974358,
|
| 13387 |
+
"grad_norm": 1.5826025009155273,
|
| 13388 |
+
"learning_rate": 2.7310819892094742e-05,
|
| 13389 |
+
"loss": 1.8546,
|
| 13390 |
+
"step": 171500
|
| 13391 |
+
},
|
| 13392 |
+
{
|
| 13393 |
+
"epoch": 0.03237347830697872,
|
| 13394 |
+
"grad_norm": 2.160349130630493,
|
| 13395 |
+
"learning_rate": 2.7288773292122827e-05,
|
| 13396 |
+
"loss": 1.8623,
|
| 13397 |
+
"step": 171600
|
| 13398 |
+
},
|
| 13399 |
+
{
|
| 13400 |
+
"epoch": 0.032652560016521635,
|
| 13401 |
+
"grad_norm": 1.6130859851837158,
|
| 13402 |
+
"learning_rate": 2.726672489701696e-05,
|
| 13403 |
+
"loss": 1.8629,
|
| 13404 |
+
"step": 171700
|
| 13405 |
+
},
|
| 13406 |
+
{
|
| 13407 |
+
"epoch": 0.03293164172606456,
|
| 13408 |
+
"grad_norm": 1.619787335395813,
|
| 13409 |
+
"learning_rate": 2.7244674724070163e-05,
|
| 13410 |
+
"loss": 1.8646,
|
| 13411 |
+
"step": 171800
|
| 13412 |
+
},
|
| 13413 |
+
{
|
| 13414 |
+
"epoch": 0.03321072343560748,
|
| 13415 |
+
"grad_norm": 2.099820375442505,
|
| 13416 |
+
"learning_rate": 2.722262279057687e-05,
|
| 13417 |
+
"loss": 1.8679,
|
| 13418 |
+
"step": 171900
|
| 13419 |
+
},
|
| 13420 |
+
{
|
| 13421 |
+
"epoch": 0.033489805145150396,
|
| 13422 |
+
"grad_norm": 1.7083640098571777,
|
| 13423 |
+
"learning_rate": 2.720056911383287e-05,
|
| 13424 |
+
"loss": 1.8554,
|
| 13425 |
+
"step": 172000
|
| 13426 |
+
},
|
| 13427 |
+
{
|
| 13428 |
+
"epoch": 0.033489805145150396,
|
| 13429 |
+
"eval_loss": 2.1523571014404297,
|
| 13430 |
+
"eval_runtime": 52.1491,
|
| 13431 |
+
"eval_samples_per_second": 195.478,
|
| 13432 |
+
"eval_steps_per_second": 1.534,
|
| 13433 |
+
"step": 172000
|
| 13434 |
+
},
|
| 13435 |
+
{
|
| 13436 |
+
"epoch": 0.033768886854693314,
|
| 13437 |
+
"grad_norm": 1.5392628908157349,
|
| 13438 |
+
"learning_rate": 2.717851371113534e-05,
|
| 13439 |
+
"loss": 1.8658,
|
| 13440 |
+
"step": 172100
|
| 13441 |
+
},
|
| 13442 |
+
{
|
| 13443 |
+
"epoch": 0.03404796856423624,
|
| 13444 |
+
"grad_norm": 2.007720708847046,
|
| 13445 |
+
"learning_rate": 2.715645659978281e-05,
|
| 13446 |
+
"loss": 1.861,
|
| 13447 |
+
"step": 172200
|
| 13448 |
+
},
|
| 13449 |
+
{
|
| 13450 |
+
"epoch": 0.03432705027377916,
|
| 13451 |
+
"grad_norm": 1.566613793373108,
|
| 13452 |
+
"learning_rate": 2.7134397797075145e-05,
|
| 13453 |
+
"loss": 1.8669,
|
| 13454 |
+
"step": 172300
|
| 13455 |
+
},
|
| 13456 |
+
{
|
| 13457 |
+
"epoch": 0.034606131983322075,
|
| 13458 |
+
"grad_norm": 1.588408350944519,
|
| 13459 |
+
"learning_rate": 2.7112337320313524e-05,
|
| 13460 |
+
"loss": 1.8568,
|
| 13461 |
+
"step": 172400
|
| 13462 |
+
},
|
| 13463 |
+
{
|
| 13464 |
+
"epoch": 0.034885213692865,
|
| 13465 |
+
"grad_norm": 1.6406699419021606,
|
| 13466 |
+
"learning_rate": 2.7090275186800474e-05,
|
| 13467 |
+
"loss": 1.8713,
|
| 13468 |
+
"step": 172500
|
| 13469 |
+
},
|
| 13470 |
+
{
|
| 13471 |
+
"epoch": 0.03516429540240792,
|
| 13472 |
+
"grad_norm": 1.5397433042526245,
|
| 13473 |
+
"learning_rate": 2.7068211413839782e-05,
|
| 13474 |
+
"loss": 1.8629,
|
| 13475 |
+
"step": 172600
|
| 13476 |
+
},
|
| 13477 |
+
{
|
| 13478 |
+
"epoch": 0.035443377111950836,
|
| 13479 |
+
"grad_norm": 1.5865190029144287,
|
| 13480 |
+
"learning_rate": 2.704614601873654e-05,
|
| 13481 |
+
"loss": 1.8579,
|
| 13482 |
+
"step": 172700
|
| 13483 |
+
},
|
| 13484 |
+
{
|
| 13485 |
+
"epoch": 0.035722458821493754,
|
| 13486 |
+
"grad_norm": 1.7077267169952393,
|
| 13487 |
+
"learning_rate": 2.702407901879712e-05,
|
| 13488 |
+
"loss": 1.8616,
|
| 13489 |
+
"step": 172800
|
| 13490 |
+
},
|
| 13491 |
+
{
|
| 13492 |
+
"epoch": 0.03600154053103668,
|
| 13493 |
+
"grad_norm": 1.727586269378662,
|
| 13494 |
+
"learning_rate": 2.7002010431329134e-05,
|
| 13495 |
+
"loss": 1.8574,
|
| 13496 |
+
"step": 172900
|
| 13497 |
+
},
|
| 13498 |
+
{
|
| 13499 |
+
"epoch": 0.036280622240579596,
|
| 13500 |
+
"grad_norm": 1.5238264799118042,
|
| 13501 |
+
"learning_rate": 2.6979940273641453e-05,
|
| 13502 |
+
"loss": 1.8595,
|
| 13503 |
+
"step": 173000
|
| 13504 |
+
},
|
| 13505 |
+
{
|
| 13506 |
+
"epoch": 0.036280622240579596,
|
| 13507 |
+
"eval_loss": 2.141134738922119,
|
| 13508 |
+
"eval_runtime": 52.1591,
|
| 13509 |
+
"eval_samples_per_second": 195.441,
|
| 13510 |
+
"eval_steps_per_second": 1.534,
|
| 13511 |
+
"step": 173000
|
| 13512 |
+
},
|
| 13513 |
+
{
|
| 13514 |
+
"epoch": 0.036559703950122514,
|
| 13515 |
+
"grad_norm": 1.5688259601593018,
|
| 13516 |
+
"learning_rate": 2.6957868563044176e-05,
|
| 13517 |
+
"loss": 1.8674,
|
| 13518 |
+
"step": 173100
|
| 13519 |
+
},
|
| 13520 |
+
{
|
| 13521 |
+
"epoch": 0.03683878565966544,
|
| 13522 |
+
"grad_norm": 1.5195534229278564,
|
| 13523 |
+
"learning_rate": 2.6935795316848612e-05,
|
| 13524 |
+
"loss": 1.8653,
|
| 13525 |
+
"step": 173200
|
| 13526 |
+
},
|
| 13527 |
+
{
|
| 13528 |
+
"epoch": 0.03711786736920836,
|
| 13529 |
+
"grad_norm": 1.6201164722442627,
|
| 13530 |
+
"learning_rate": 2.691372055236728e-05,
|
| 13531 |
+
"loss": 1.8579,
|
| 13532 |
+
"step": 173300
|
| 13533 |
+
},
|
| 13534 |
+
{
|
| 13535 |
+
"epoch": 0.037396949078751275,
|
| 13536 |
+
"grad_norm": 1.8065686225891113,
|
| 13537 |
+
"learning_rate": 2.6891644286913897e-05,
|
| 13538 |
+
"loss": 1.8755,
|
| 13539 |
+
"step": 173400
|
| 13540 |
+
},
|
| 13541 |
+
{
|
| 13542 |
+
"epoch": 0.0376760307882942,
|
| 13543 |
+
"grad_norm": 1.5661702156066895,
|
| 13544 |
+
"learning_rate": 2.6869566537803347e-05,
|
| 13545 |
+
"loss": 1.8552,
|
| 13546 |
+
"step": 173500
|
| 13547 |
+
},
|
| 13548 |
+
{
|
| 13549 |
+
"epoch": 0.03795511249783712,
|
| 13550 |
+
"grad_norm": 1.6565943956375122,
|
| 13551 |
+
"learning_rate": 2.6847487322351694e-05,
|
| 13552 |
+
"loss": 1.8664,
|
| 13553 |
+
"step": 173600
|
| 13554 |
+
},
|
| 13555 |
+
{
|
| 13556 |
+
"epoch": 0.038234194207380036,
|
| 13557 |
+
"grad_norm": 1.49613356590271,
|
| 13558 |
+
"learning_rate": 2.6825406657876123e-05,
|
| 13559 |
+
"loss": 1.8524,
|
| 13560 |
+
"step": 173700
|
| 13561 |
+
},
|
| 13562 |
+
{
|
| 13563 |
+
"epoch": 0.038513275916922954,
|
| 13564 |
+
"grad_norm": 1.5829864740371704,
|
| 13565 |
+
"learning_rate": 2.6803324561694988e-05,
|
| 13566 |
+
"loss": 1.8732,
|
| 13567 |
+
"step": 173800
|
| 13568 |
+
},
|
| 13569 |
+
{
|
| 13570 |
+
"epoch": 0.03879235762646588,
|
| 13571 |
+
"grad_norm": 1.6095563173294067,
|
| 13572 |
+
"learning_rate": 2.6781241051127738e-05,
|
| 13573 |
+
"loss": 1.8503,
|
| 13574 |
+
"step": 173900
|
| 13575 |
+
},
|
| 13576 |
+
{
|
| 13577 |
+
"epoch": 0.0390714393360088,
|
| 13578 |
+
"grad_norm": 1.5767251253128052,
|
| 13579 |
+
"learning_rate": 2.675915614349495e-05,
|
| 13580 |
+
"loss": 1.856,
|
| 13581 |
+
"step": 174000
|
| 13582 |
+
},
|
| 13583 |
+
{
|
| 13584 |
+
"epoch": 0.0390714393360088,
|
| 13585 |
+
"eval_loss": 2.1416378021240234,
|
| 13586 |
+
"eval_runtime": 52.1112,
|
| 13587 |
+
"eval_samples_per_second": 195.62,
|
| 13588 |
+
"eval_steps_per_second": 1.535,
|
| 13589 |
+
"step": 174000
|
| 13590 |
+
},
|
| 13591 |
+
{
|
| 13592 |
+
"epoch": 0.00027908170954291995,
|
| 13593 |
+
"grad_norm": 1.5513286590576172,
|
| 13594 |
+
"learning_rate": 2.6737069856118284e-05,
|
| 13595 |
+
"loss": 1.7542,
|
| 13596 |
+
"step": 174100
|
| 13597 |
+
},
|
| 13598 |
+
{
|
| 13599 |
+
"epoch": 0.0005581634190858399,
|
| 13600 |
+
"grad_norm": 1.5664585828781128,
|
| 13601 |
+
"learning_rate": 2.67149822063205e-05,
|
| 13602 |
+
"loss": 1.7515,
|
| 13603 |
+
"step": 174200
|
| 13604 |
+
},
|
| 13605 |
+
{
|
| 13606 |
+
"epoch": 0.0008372451286287599,
|
| 13607 |
+
"grad_norm": 1.5423948764801025,
|
| 13608 |
+
"learning_rate": 2.66928932114254e-05,
|
| 13609 |
+
"loss": 1.7557,
|
| 13610 |
+
"step": 174300
|
| 13611 |
+
},
|
| 13612 |
+
{
|
| 13613 |
+
"epoch": 0.0011163268381716798,
|
| 13614 |
+
"grad_norm": 1.5535671710968018,
|
| 13615 |
+
"learning_rate": 2.667080288875788e-05,
|
| 13616 |
+
"loss": 1.7569,
|
| 13617 |
+
"step": 174400
|
| 13618 |
+
},
|
| 13619 |
+
{
|
| 13620 |
+
"epoch": 0.0013954085477146,
|
| 13621 |
+
"grad_norm": 1.5592520236968994,
|
| 13622 |
+
"learning_rate": 2.6648711255643828e-05,
|
| 13623 |
+
"loss": 1.7506,
|
| 13624 |
+
"step": 174500
|
| 13625 |
+
},
|
| 13626 |
+
{
|
| 13627 |
+
"epoch": 0.0016744902572575198,
|
| 13628 |
+
"grad_norm": 1.5440510511398315,
|
| 13629 |
+
"learning_rate": 2.6626618329410198e-05,
|
| 13630 |
+
"loss": 1.7618,
|
| 13631 |
+
"step": 174600
|
| 13632 |
+
},
|
| 13633 |
+
{
|
| 13634 |
+
"epoch": 0.00195357196680044,
|
| 13635 |
+
"grad_norm": 1.54314124584198,
|
| 13636 |
+
"learning_rate": 2.6604524127384937e-05,
|
| 13637 |
+
"loss": 1.7491,
|
| 13638 |
+
"step": 174700
|
| 13639 |
+
},
|
| 13640 |
+
{
|
| 13641 |
+
"epoch": 0.0022326536763433596,
|
| 13642 |
+
"grad_norm": 1.592208743095398,
|
| 13643 |
+
"learning_rate": 2.658242866689702e-05,
|
| 13644 |
+
"loss": 1.7458,
|
| 13645 |
+
"step": 174800
|
| 13646 |
+
},
|
| 13647 |
+
{
|
| 13648 |
+
"epoch": 0.0025117353858862797,
|
| 13649 |
+
"grad_norm": 1.5204849243164062,
|
| 13650 |
+
"learning_rate": 2.6560331965276363e-05,
|
| 13651 |
+
"loss": 1.7523,
|
| 13652 |
+
"step": 174900
|
| 13653 |
+
},
|
| 13654 |
+
{
|
| 13655 |
+
"epoch": 0.0027908170954292,
|
| 13656 |
+
"grad_norm": 1.5259612798690796,
|
| 13657 |
+
"learning_rate": 2.653823403985391e-05,
|
| 13658 |
+
"loss": 1.7535,
|
| 13659 |
+
"step": 175000
|
| 13660 |
+
},
|
| 13661 |
+
{
|
| 13662 |
+
"epoch": 0.0027908170954292,
|
| 13663 |
+
"eval_loss": 2.1326749324798584,
|
| 13664 |
+
"eval_runtime": 52.049,
|
| 13665 |
+
"eval_samples_per_second": 195.854,
|
| 13666 |
+
"eval_steps_per_second": 1.537,
|
| 13667 |
+
"step": 175000
|
| 13668 |
+
},
|
| 13669 |
+
{
|
| 13670 |
+
"epoch": 0.00306989880497212,
|
| 13671 |
+
"grad_norm": 1.52047598361969,
|
| 13672 |
+
"learning_rate": 2.651613490796152e-05,
|
| 13673 |
+
"loss": 1.7447,
|
| 13674 |
+
"step": 175100
|
| 13675 |
+
},
|
| 13676 |
+
{
|
| 13677 |
+
"epoch": 0.0033489805145150396,
|
| 13678 |
+
"grad_norm": 1.5134586095809937,
|
| 13679 |
+
"learning_rate": 2.6494034586932027e-05,
|
| 13680 |
+
"loss": 1.7452,
|
| 13681 |
+
"step": 175200
|
| 13682 |
+
},
|
| 13683 |
+
{
|
| 13684 |
+
"epoch": 0.0036280622240579597,
|
| 13685 |
+
"grad_norm": 1.572095513343811,
|
| 13686 |
+
"learning_rate": 2.6471933094099177e-05,
|
| 13687 |
+
"loss": 1.7571,
|
| 13688 |
+
"step": 175300
|
| 13689 |
+
},
|
| 13690 |
+
{
|
| 13691 |
+
"epoch": 0.00390714393360088,
|
| 13692 |
+
"grad_norm": 1.5933750867843628,
|
| 13693 |
+
"learning_rate": 2.6449830446797653e-05,
|
| 13694 |
+
"loss": 1.745,
|
| 13695 |
+
"step": 175400
|
| 13696 |
+
},
|
| 13697 |
+
{
|
| 13698 |
+
"epoch": 0.0041862256431437995,
|
| 13699 |
+
"grad_norm": 1.6601353883743286,
|
| 13700 |
+
"learning_rate": 2.6427726662363023e-05,
|
| 13701 |
+
"loss": 1.7462,
|
| 13702 |
+
"step": 175500
|
| 13703 |
+
},
|
| 13704 |
+
{
|
| 13705 |
+
"epoch": 0.004465307352686719,
|
| 13706 |
+
"grad_norm": 1.5466818809509277,
|
| 13707 |
+
"learning_rate": 2.640562175813177e-05,
|
| 13708 |
+
"loss": 1.7573,
|
| 13709 |
+
"step": 175600
|
| 13710 |
+
},
|
| 13711 |
+
{
|
| 13712 |
+
"epoch": 0.00474438906222964,
|
| 13713 |
+
"grad_norm": 1.5273200273513794,
|
| 13714 |
+
"learning_rate": 2.6383515751441234e-05,
|
| 13715 |
+
"loss": 1.7578,
|
| 13716 |
+
"step": 175700
|
| 13717 |
+
},
|
| 13718 |
+
{
|
| 13719 |
+
"epoch": 0.005023470771772559,
|
| 13720 |
+
"grad_norm": 1.609778881072998,
|
| 13721 |
+
"learning_rate": 2.636140865962965e-05,
|
| 13722 |
+
"loss": 1.7513,
|
| 13723 |
+
"step": 175800
|
| 13724 |
+
},
|
| 13725 |
+
{
|
| 13726 |
+
"epoch": 0.00530255248131548,
|
| 13727 |
+
"grad_norm": 1.6019160747528076,
|
| 13728 |
+
"learning_rate": 2.633930050003606e-05,
|
| 13729 |
+
"loss": 1.7557,
|
| 13730 |
+
"step": 175900
|
| 13731 |
+
},
|
| 13732 |
+
{
|
| 13733 |
+
"epoch": 0.0055816341908584,
|
| 13734 |
+
"grad_norm": 1.5547572374343872,
|
| 13735 |
+
"learning_rate": 2.6317191290000383e-05,
|
| 13736 |
+
"loss": 1.7645,
|
| 13737 |
+
"step": 176000
|
| 13738 |
+
},
|
| 13739 |
+
{
|
| 13740 |
+
"epoch": 0.0055816341908584,
|
| 13741 |
+
"eval_loss": 2.141494035720825,
|
| 13742 |
+
"eval_runtime": 51.4645,
|
| 13743 |
+
"eval_samples_per_second": 198.078,
|
| 13744 |
+
"eval_steps_per_second": 1.554,
|
| 13745 |
+
"step": 176000
|
| 13746 |
+
},
|
| 13747 |
+
{
|
| 13748 |
+
"epoch": 0.005860715900401319,
|
| 13749 |
+
"grad_norm": 1.6100679636001587,
|
| 13750 |
+
"learning_rate": 2.629508104686334e-05,
|
| 13751 |
+
"loss": 1.7566,
|
| 13752 |
+
"step": 176100
|
| 13753 |
+
},
|
| 13754 |
+
{
|
| 13755 |
+
"epoch": 0.00613979760994424,
|
| 13756 |
+
"grad_norm": 1.5966265201568604,
|
| 13757 |
+
"learning_rate": 2.6272969787966466e-05,
|
| 13758 |
+
"loss": 1.7511,
|
| 13759 |
+
"step": 176200
|
| 13760 |
+
},
|
| 13761 |
+
{
|
| 13762 |
+
"epoch": 0.0064188793194871595,
|
| 13763 |
+
"grad_norm": 1.5519967079162598,
|
| 13764 |
+
"learning_rate": 2.6250857530652113e-05,
|
| 13765 |
+
"loss": 1.7534,
|
| 13766 |
+
"step": 176300
|
| 13767 |
+
},
|
| 13768 |
+
{
|
| 13769 |
+
"epoch": 0.006697961029030079,
|
| 13770 |
+
"grad_norm": 1.5537617206573486,
|
| 13771 |
+
"learning_rate": 2.6228744292263367e-05,
|
| 13772 |
+
"loss": 1.7448,
|
| 13773 |
+
"step": 176400
|
| 13774 |
+
},
|
| 13775 |
+
{
|
| 13776 |
+
"epoch": 0.006977042738573,
|
| 13777 |
+
"grad_norm": 1.5397429466247559,
|
| 13778 |
+
"learning_rate": 2.6206630090144153e-05,
|
| 13779 |
+
"loss": 1.7456,
|
| 13780 |
+
"step": 176500
|
| 13781 |
+
},
|
| 13782 |
+
{
|
| 13783 |
+
"epoch": 0.0072561244481159195,
|
| 13784 |
+
"grad_norm": 1.5131994485855103,
|
| 13785 |
+
"learning_rate": 2.618451494163908e-05,
|
| 13786 |
+
"loss": 1.7472,
|
| 13787 |
+
"step": 176600
|
| 13788 |
+
},
|
| 13789 |
+
{
|
| 13790 |
+
"epoch": 0.007535206157658839,
|
| 13791 |
+
"grad_norm": 1.553226113319397,
|
| 13792 |
+
"learning_rate": 2.6162398864093553e-05,
|
| 13793 |
+
"loss": 1.7588,
|
| 13794 |
+
"step": 176700
|
| 13795 |
+
},
|
| 13796 |
+
{
|
| 13797 |
+
"epoch": 0.00781428786720176,
|
| 13798 |
+
"grad_norm": 1.5782634019851685,
|
| 13799 |
+
"learning_rate": 2.6140281874853666e-05,
|
| 13800 |
+
"loss": 1.7498,
|
| 13801 |
+
"step": 176800
|
| 13802 |
+
},
|
| 13803 |
+
{
|
| 13804 |
+
"epoch": 0.00809336957674468,
|
| 13805 |
+
"grad_norm": 1.5181629657745361,
|
| 13806 |
+
"learning_rate": 2.6118163991266275e-05,
|
| 13807 |
+
"loss": 1.7525,
|
| 13808 |
+
"step": 176900
|
| 13809 |
+
},
|
| 13810 |
+
{
|
| 13811 |
+
"epoch": 0.008372451286287599,
|
| 13812 |
+
"grad_norm": 1.622118353843689,
|
| 13813 |
+
"learning_rate": 2.6096045230678888e-05,
|
| 13814 |
+
"loss": 1.7472,
|
| 13815 |
+
"step": 177000
|
| 13816 |
+
},
|
| 13817 |
+
{
|
| 13818 |
+
"epoch": 0.008372451286287599,
|
| 13819 |
+
"eval_loss": 2.1567530632019043,
|
| 13820 |
+
"eval_runtime": 51.4987,
|
| 13821 |
+
"eval_samples_per_second": 197.947,
|
| 13822 |
+
"eval_steps_per_second": 1.553,
|
| 13823 |
+
"step": 177000
|
| 13824 |
+
},
|
| 13825 |
+
{
|
| 13826 |
+
"epoch": 0.008651532995830519,
|
| 13827 |
+
"grad_norm": 1.5844262838363647,
|
| 13828 |
+
"learning_rate": 2.6073925610439738e-05,
|
| 13829 |
+
"loss": 1.7489,
|
| 13830 |
+
"step": 177100
|
| 13831 |
+
},
|
| 13832 |
+
{
|
| 13833 |
+
"epoch": 0.008930614705373438,
|
| 13834 |
+
"grad_norm": 1.4944721460342407,
|
| 13835 |
+
"learning_rate": 2.6051805147897713e-05,
|
| 13836 |
+
"loss": 1.7535,
|
| 13837 |
+
"step": 177200
|
| 13838 |
+
},
|
| 13839 |
+
{
|
| 13840 |
+
"epoch": 0.00920969641491636,
|
| 13841 |
+
"grad_norm": 1.607365608215332,
|
| 13842 |
+
"learning_rate": 2.602968386040236e-05,
|
| 13843 |
+
"loss": 1.7476,
|
| 13844 |
+
"step": 177300
|
| 13845 |
+
},
|
| 13846 |
+
{
|
| 13847 |
+
"epoch": 0.00948877812445928,
|
| 13848 |
+
"grad_norm": 1.5790349245071411,
|
| 13849 |
+
"learning_rate": 2.6007561765303878e-05,
|
| 13850 |
+
"loss": 1.7465,
|
| 13851 |
+
"step": 177400
|
| 13852 |
+
},
|
| 13853 |
+
{
|
| 13854 |
+
"epoch": 0.0097678598340022,
|
| 13855 |
+
"grad_norm": 1.5833547115325928,
|
| 13856 |
+
"learning_rate": 2.5985438879953107e-05,
|
| 13857 |
+
"loss": 1.7581,
|
| 13858 |
+
"step": 177500
|
| 13859 |
+
},
|
| 13860 |
+
{
|
| 13861 |
+
"epoch": 0.010046941543545119,
|
| 13862 |
+
"grad_norm": 1.5244640111923218,
|
| 13863 |
+
"learning_rate": 2.5963315221701496e-05,
|
| 13864 |
+
"loss": 1.7489,
|
| 13865 |
+
"step": 177600
|
| 13866 |
+
},
|
| 13867 |
+
{
|
| 13868 |
+
"epoch": 0.010326023253088039,
|
| 13869 |
+
"grad_norm": 1.6332496404647827,
|
| 13870 |
+
"learning_rate": 2.5941190807901117e-05,
|
| 13871 |
+
"loss": 1.7593,
|
| 13872 |
+
"step": 177700
|
| 13873 |
+
},
|
| 13874 |
+
{
|
| 13875 |
+
"epoch": 0.01060510496263096,
|
| 13876 |
+
"grad_norm": 1.4967930316925049,
|
| 13877 |
+
"learning_rate": 2.5919065655904606e-05,
|
| 13878 |
+
"loss": 1.7487,
|
| 13879 |
+
"step": 177800
|
| 13880 |
+
},
|
| 13881 |
+
{
|
| 13882 |
+
"epoch": 0.01088418667217388,
|
| 13883 |
+
"grad_norm": 1.5874158143997192,
|
| 13884 |
+
"learning_rate": 2.5896939783065198e-05,
|
| 13885 |
+
"loss": 1.7488,
|
| 13886 |
+
"step": 177900
|
| 13887 |
+
},
|
| 13888 |
+
{
|
| 13889 |
+
"epoch": 0.0111632683817168,
|
| 13890 |
+
"grad_norm": 1.6334315538406372,
|
| 13891 |
+
"learning_rate": 2.587481320673669e-05,
|
| 13892 |
+
"loss": 1.7558,
|
| 13893 |
+
"step": 178000
|
| 13894 |
+
},
|
| 13895 |
+
{
|
| 13896 |
+
"epoch": 0.0111632683817168,
|
| 13897 |
+
"eval_loss": 2.1407663822174072,
|
| 13898 |
+
"eval_runtime": 51.564,
|
| 13899 |
+
"eval_samples_per_second": 197.696,
|
| 13900 |
+
"eval_steps_per_second": 1.551,
|
| 13901 |
+
"step": 178000
|
| 13902 |
+
},
|
| 13903 |
+
{
|
| 13904 |
+
"epoch": 0.011442350091259719,
|
| 13905 |
+
"grad_norm": 1.5070706605911255,
|
| 13906 |
+
"learning_rate": 2.5852685944273437e-05,
|
| 13907 |
+
"loss": 1.7515,
|
| 13908 |
+
"step": 178100
|
| 13909 |
+
},
|
| 13910 |
+
{
|
| 13911 |
+
"epoch": 0.011721431800802639,
|
| 13912 |
+
"grad_norm": 1.675197958946228,
|
| 13913 |
+
"learning_rate": 2.583055801303031e-05,
|
| 13914 |
+
"loss": 1.7517,
|
| 13915 |
+
"step": 178200
|
| 13916 |
+
},
|
| 13917 |
+
{
|
| 13918 |
+
"epoch": 0.012000513510345558,
|
| 13919 |
+
"grad_norm": 1.6129719018936157,
|
| 13920 |
+
"learning_rate": 2.5808429430362734e-05,
|
| 13921 |
+
"loss": 1.739,
|
| 13922 |
+
"step": 178300
|
| 13923 |
+
},
|
| 13924 |
+
{
|
| 13925 |
+
"epoch": 0.01227959521988848,
|
| 13926 |
+
"grad_norm": 1.6314342021942139,
|
| 13927 |
+
"learning_rate": 2.5786300213626623e-05,
|
| 13928 |
+
"loss": 1.7373,
|
| 13929 |
+
"step": 178400
|
| 13930 |
+
},
|
| 13931 |
+
{
|
| 13932 |
+
"epoch": 0.0125586769294314,
|
| 13933 |
+
"grad_norm": 1.4758597612380981,
|
| 13934 |
+
"learning_rate": 2.576417038017841e-05,
|
| 13935 |
+
"loss": 1.7512,
|
| 13936 |
+
"step": 178500
|
| 13937 |
+
},
|
| 13938 |
+
{
|
| 13939 |
+
"epoch": 0.012837758638974319,
|
| 13940 |
+
"grad_norm": 1.6322437524795532,
|
| 13941 |
+
"learning_rate": 2.574203994737498e-05,
|
| 13942 |
+
"loss": 1.7529,
|
| 13943 |
+
"step": 178600
|
| 13944 |
+
},
|
| 13945 |
+
{
|
| 13946 |
+
"epoch": 0.013116840348517239,
|
| 13947 |
+
"grad_norm": 1.6611186265945435,
|
| 13948 |
+
"learning_rate": 2.5719908932573716e-05,
|
| 13949 |
+
"loss": 1.7529,
|
| 13950 |
+
"step": 178700
|
| 13951 |
+
},
|
| 13952 |
+
{
|
| 13953 |
+
"epoch": 0.013395922058060158,
|
| 13954 |
+
"grad_norm": 1.6254630088806152,
|
| 13955 |
+
"learning_rate": 2.5697777353132434e-05,
|
| 13956 |
+
"loss": 1.7548,
|
| 13957 |
+
"step": 178800
|
| 13958 |
+
},
|
| 13959 |
+
{
|
| 13960 |
+
"epoch": 0.013675003767603078,
|
| 13961 |
+
"grad_norm": 1.6417994499206543,
|
| 13962 |
+
"learning_rate": 2.567564522640942e-05,
|
| 13963 |
+
"loss": 1.7501,
|
| 13964 |
+
"step": 178900
|
| 13965 |
+
},
|
| 13966 |
+
{
|
| 13967 |
+
"epoch": 0.013954085477146,
|
| 13968 |
+
"grad_norm": 1.5359156131744385,
|
| 13969 |
+
"learning_rate": 2.5653512569763377e-05,
|
| 13970 |
+
"loss": 1.7562,
|
| 13971 |
+
"step": 179000
|
| 13972 |
+
},
|
| 13973 |
+
{
|
| 13974 |
+
"epoch": 0.013954085477146,
|
| 13975 |
+
"eval_loss": 2.144591808319092,
|
| 13976 |
+
"eval_runtime": 51.5364,
|
| 13977 |
+
"eval_samples_per_second": 197.802,
|
| 13978 |
+
"eval_steps_per_second": 1.552,
|
| 13979 |
+
"step": 179000
|
| 13980 |
+
},
|
| 13981 |
+
{
|
| 13982 |
+
"epoch": 0.01423316718668892,
|
| 13983 |
+
"grad_norm": 1.5880595445632935,
|
| 13984 |
+
"learning_rate": 2.5631379400553416e-05,
|
| 13985 |
+
"loss": 1.75,
|
| 13986 |
+
"step": 179100
|
| 13987 |
+
},
|
| 13988 |
+
{
|
| 13989 |
+
"epoch": 0.014512248896231839,
|
| 13990 |
+
"grad_norm": 1.6134679317474365,
|
| 13991 |
+
"learning_rate": 2.560924573613906e-05,
|
| 13992 |
+
"loss": 1.7508,
|
| 13993 |
+
"step": 179200
|
| 13994 |
+
},
|
| 13995 |
+
{
|
| 13996 |
+
"epoch": 0.014791330605774759,
|
| 13997 |
+
"grad_norm": 1.5464352369308472,
|
| 13998 |
+
"learning_rate": 2.5587111593880205e-05,
|
| 13999 |
+
"loss": 1.7502,
|
| 14000 |
+
"step": 179300
|
| 14001 |
+
},
|
| 14002 |
+
{
|
| 14003 |
+
"epoch": 0.015070412315317678,
|
| 14004 |
+
"grad_norm": 1.573649525642395,
|
| 14005 |
+
"learning_rate": 2.556497699113714e-05,
|
| 14006 |
+
"loss": 1.7435,
|
| 14007 |
+
"step": 179400
|
| 14008 |
+
},
|
| 14009 |
+
{
|
| 14010 |
+
"epoch": 0.015349494024860598,
|
| 14011 |
+
"grad_norm": 1.5665711164474487,
|
| 14012 |
+
"learning_rate": 2.554284194527051e-05,
|
| 14013 |
+
"loss": 1.7462,
|
| 14014 |
+
"step": 179500
|
| 14015 |
+
},
|
| 14016 |
+
{
|
| 14017 |
+
"epoch": 0.01562857573440352,
|
| 14018 |
+
"grad_norm": 1.606072187423706,
|
| 14019 |
+
"learning_rate": 2.5520706473641316e-05,
|
| 14020 |
+
"loss": 1.7516,
|
| 14021 |
+
"step": 179600
|
| 14022 |
+
},
|
| 14023 |
+
{
|
| 14024 |
+
"epoch": 0.015907657443946437,
|
| 14025 |
+
"grad_norm": 1.5898959636688232,
|
| 14026 |
+
"learning_rate": 2.549857059361086e-05,
|
| 14027 |
+
"loss": 1.7482,
|
| 14028 |
+
"step": 179700
|
| 14029 |
+
},
|
| 14030 |
+
{
|
| 14031 |
+
"epoch": 0.01618673915348936,
|
| 14032 |
+
"grad_norm": 1.6288598775863647,
|
| 14033 |
+
"learning_rate": 2.547643432254081e-05,
|
| 14034 |
+
"loss": 1.7365,
|
| 14035 |
+
"step": 179800
|
| 14036 |
+
},
|
| 14037 |
+
{
|
| 14038 |
+
"epoch": 0.01646582086303228,
|
| 14039 |
+
"grad_norm": 1.5765552520751953,
|
| 14040 |
+
"learning_rate": 2.545429767779311e-05,
|
| 14041 |
+
"loss": 1.7346,
|
| 14042 |
+
"step": 179900
|
| 14043 |
+
},
|
| 14044 |
+
{
|
| 14045 |
+
"epoch": 0.016744902572575198,
|
| 14046 |
+
"grad_norm": 1.5909677743911743,
|
| 14047 |
+
"learning_rate": 2.5432160676729994e-05,
|
| 14048 |
+
"loss": 1.7493,
|
| 14049 |
+
"step": 180000
|
| 14050 |
+
},
|
| 14051 |
+
{
|
| 14052 |
+
"epoch": 0.016744902572575198,
|
| 14053 |
+
"eval_loss": 2.1469063758850098,
|
| 14054 |
+
"eval_runtime": 52.5101,
|
| 14055 |
+
"eval_samples_per_second": 194.134,
|
| 14056 |
+
"eval_steps_per_second": 1.524,
|
| 14057 |
+
"step": 180000
|
| 14058 |
+
},
|
| 14059 |
+
{
|
| 14060 |
+
"epoch": 0.01702398428211812,
|
| 14061 |
+
"grad_norm": 1.6108888387680054,
|
| 14062 |
+
"learning_rate": 2.5410023336713996e-05,
|
| 14063 |
+
"loss": 1.749,
|
| 14064 |
+
"step": 180100
|
| 14065 |
+
},
|
| 14066 |
+
{
|
| 14067 |
+
"epoch": 0.017303065991661037,
|
| 14068 |
+
"grad_norm": 1.5427972078323364,
|
| 14069 |
+
"learning_rate": 2.538788567510791e-05,
|
| 14070 |
+
"loss": 1.738,
|
| 14071 |
+
"step": 180200
|
| 14072 |
+
},
|
| 14073 |
+
{
|
| 14074 |
+
"epoch": 0.01758214770120396,
|
| 14075 |
+
"grad_norm": 1.5925029516220093,
|
| 14076 |
+
"learning_rate": 2.5365747709274767e-05,
|
| 14077 |
+
"loss": 1.7418,
|
| 14078 |
+
"step": 180300
|
| 14079 |
+
},
|
| 14080 |
+
{
|
| 14081 |
+
"epoch": 0.017861229410746877,
|
| 14082 |
+
"grad_norm": 1.5784283876419067,
|
| 14083 |
+
"learning_rate": 2.5343609456577867e-05,
|
| 14084 |
+
"loss": 1.7417,
|
| 14085 |
+
"step": 180400
|
| 14086 |
+
},
|
| 14087 |
+
{
|
| 14088 |
+
"epoch": 0.018140311120289798,
|
| 14089 |
+
"grad_norm": 1.623561978340149,
|
| 14090 |
+
"learning_rate": 2.53214709343807e-05,
|
| 14091 |
+
"loss": 1.7443,
|
| 14092 |
+
"step": 180500
|
| 14093 |
+
},
|
| 14094 |
+
{
|
| 14095 |
+
"epoch": 0.01841939282983272,
|
| 14096 |
+
"grad_norm": 1.6505674123764038,
|
| 14097 |
+
"learning_rate": 2.5299332160046985e-05,
|
| 14098 |
+
"loss": 1.7454,
|
| 14099 |
+
"step": 180600
|
| 14100 |
+
},
|
| 14101 |
+
{
|
| 14102 |
+
"epoch": 0.018698474539375638,
|
| 14103 |
+
"grad_norm": 1.5555040836334229,
|
| 14104 |
+
"learning_rate": 2.5277193150940638e-05,
|
| 14105 |
+
"loss": 1.7416,
|
| 14106 |
+
"step": 180700
|
| 14107 |
+
},
|
| 14108 |
+
{
|
| 14109 |
+
"epoch": 0.01897755624891856,
|
| 14110 |
+
"grad_norm": 1.6162723302841187,
|
| 14111 |
+
"learning_rate": 2.525505392442577e-05,
|
| 14112 |
+
"loss": 1.7433,
|
| 14113 |
+
"step": 180800
|
| 14114 |
+
},
|
| 14115 |
+
{
|
| 14116 |
+
"epoch": 0.019256637958461477,
|
| 14117 |
+
"grad_norm": 1.5440572500228882,
|
| 14118 |
+
"learning_rate": 2.523291449786663e-05,
|
| 14119 |
+
"loss": 1.7438,
|
| 14120 |
+
"step": 180900
|
| 14121 |
+
},
|
| 14122 |
+
{
|
| 14123 |
+
"epoch": 0.0195357196680044,
|
| 14124 |
+
"grad_norm": 1.596146583557129,
|
| 14125 |
+
"learning_rate": 2.5210774888627664e-05,
|
| 14126 |
+
"loss": 1.7425,
|
| 14127 |
+
"step": 181000
|
| 14128 |
+
},
|
| 14129 |
+
{
|
| 14130 |
+
"epoch": 0.0195357196680044,
|
| 14131 |
+
"eval_loss": 2.140672206878662,
|
| 14132 |
+
"eval_runtime": 51.8004,
|
| 14133 |
+
"eval_samples_per_second": 196.794,
|
| 14134 |
+
"eval_steps_per_second": 1.544,
|
| 14135 |
+
"step": 181000
|
| 14136 |
+
},
|
| 14137 |
+
{
|
| 14138 |
+
"epoch": 0.01981480137754732,
|
| 14139 |
+
"grad_norm": 1.6086748838424683,
|
| 14140 |
+
"learning_rate": 2.5188635114073434e-05,
|
| 14141 |
+
"loss": 1.7488,
|
| 14142 |
+
"step": 181100
|
| 14143 |
+
},
|
| 14144 |
+
{
|
| 14145 |
+
"epoch": 0.020093883087090238,
|
| 14146 |
+
"grad_norm": 1.564663290977478,
|
| 14147 |
+
"learning_rate": 2.516649519156864e-05,
|
| 14148 |
+
"loss": 1.7452,
|
| 14149 |
+
"step": 181200
|
| 14150 |
+
},
|
| 14151 |
+
{
|
| 14152 |
+
"epoch": 0.02037296479663316,
|
| 14153 |
+
"grad_norm": 1.5975944995880127,
|
| 14154 |
+
"learning_rate": 2.51443551384781e-05,
|
| 14155 |
+
"loss": 1.7419,
|
| 14156 |
+
"step": 181300
|
| 14157 |
+
},
|
| 14158 |
+
{
|
| 14159 |
+
"epoch": 0.020652046506176077,
|
| 14160 |
+
"grad_norm": 1.6056960821151733,
|
| 14161 |
+
"learning_rate": 2.5122214972166724e-05,
|
| 14162 |
+
"loss": 1.7536,
|
| 14163 |
+
"step": 181400
|
| 14164 |
+
},
|
| 14165 |
+
{
|
| 14166 |
+
"epoch": 0.020931128215719,
|
| 14167 |
+
"grad_norm": 1.6348010301589966,
|
| 14168 |
+
"learning_rate": 2.5100074709999526e-05,
|
| 14169 |
+
"loss": 1.7505,
|
| 14170 |
+
"step": 181500
|
| 14171 |
+
},
|
| 14172 |
+
{
|
| 14173 |
+
"epoch": 0.02121020992526192,
|
| 14174 |
+
"grad_norm": 1.4651880264282227,
|
| 14175 |
+
"learning_rate": 2.5077934369341594e-05,
|
| 14176 |
+
"loss": 1.7474,
|
| 14177 |
+
"step": 181600
|
| 14178 |
+
},
|
| 14179 |
+
{
|
| 14180 |
+
"epoch": 0.021489291634804838,
|
| 14181 |
+
"grad_norm": 1.6000345945358276,
|
| 14182 |
+
"learning_rate": 2.505579396755806e-05,
|
| 14183 |
+
"loss": 1.7455,
|
| 14184 |
+
"step": 181700
|
| 14185 |
+
},
|
| 14186 |
+
{
|
| 14187 |
+
"epoch": 0.02176837334434776,
|
| 14188 |
+
"grad_norm": 1.6549137830734253,
|
| 14189 |
+
"learning_rate": 2.503365352201413e-05,
|
| 14190 |
+
"loss": 1.7404,
|
| 14191 |
+
"step": 181800
|
| 14192 |
+
},
|
| 14193 |
+
{
|
| 14194 |
+
"epoch": 0.022047455053890677,
|
| 14195 |
+
"grad_norm": 1.6172484159469604,
|
| 14196 |
+
"learning_rate": 2.5011513050075014e-05,
|
| 14197 |
+
"loss": 1.7457,
|
| 14198 |
+
"step": 181900
|
| 14199 |
+
},
|
| 14200 |
+
{
|
| 14201 |
+
"epoch": 0.0223265367634336,
|
| 14202 |
+
"grad_norm": 1.6283797025680542,
|
| 14203 |
+
"learning_rate": 2.4989372569105962e-05,
|
| 14204 |
+
"loss": 1.7411,
|
| 14205 |
+
"step": 182000
|
| 14206 |
+
},
|
| 14207 |
+
{
|
| 14208 |
+
"epoch": 0.0223265367634336,
|
| 14209 |
+
"eval_loss": 2.1432528495788574,
|
| 14210 |
+
"eval_runtime": 51.7742,
|
| 14211 |
+
"eval_samples_per_second": 196.894,
|
| 14212 |
+
"eval_steps_per_second": 1.545,
|
| 14213 |
+
"step": 182000
|
| 14214 |
+
},
|
| 14215 |
+
{
|
| 14216 |
+
"epoch": 0.022605618472976517,
|
| 14217 |
+
"grad_norm": 1.5319279432296753,
|
| 14218 |
+
"learning_rate": 2.4967232096472236e-05,
|
| 14219 |
+
"loss": 1.76,
|
| 14220 |
+
"step": 182100
|
| 14221 |
+
},
|
| 14222 |
+
{
|
| 14223 |
+
"epoch": 0.022884700182519438,
|
| 14224 |
+
"grad_norm": 1.600860595703125,
|
| 14225 |
+
"learning_rate": 2.4945091649539086e-05,
|
| 14226 |
+
"loss": 1.7416,
|
| 14227 |
+
"step": 182200
|
| 14228 |
+
},
|
| 14229 |
+
{
|
| 14230 |
+
"epoch": 0.02316378189206236,
|
| 14231 |
+
"grad_norm": 1.5592856407165527,
|
| 14232 |
+
"learning_rate": 2.4922951245671723e-05,
|
| 14233 |
+
"loss": 1.7421,
|
| 14234 |
+
"step": 182300
|
| 14235 |
+
},
|
| 14236 |
+
{
|
| 14237 |
+
"epoch": 0.023442863601605277,
|
| 14238 |
+
"grad_norm": 1.5361909866333008,
|
| 14239 |
+
"learning_rate": 2.4900810902235356e-05,
|
| 14240 |
+
"loss": 1.7436,
|
| 14241 |
+
"step": 182400
|
| 14242 |
+
},
|
| 14243 |
+
{
|
| 14244 |
+
"epoch": 0.0237219453111482,
|
| 14245 |
+
"grad_norm": 1.526672124862671,
|
| 14246 |
+
"learning_rate": 2.4878670636595117e-05,
|
| 14247 |
+
"loss": 1.7418,
|
| 14248 |
+
"step": 182500
|
| 14249 |
+
},
|
| 14250 |
+
{
|
| 14251 |
+
"epoch": 0.024001027020691117,
|
| 14252 |
+
"grad_norm": 1.5167595148086548,
|
| 14253 |
+
"learning_rate": 2.4856530466116112e-05,
|
| 14254 |
+
"loss": 1.7389,
|
| 14255 |
+
"step": 182600
|
| 14256 |
+
},
|
| 14257 |
+
{
|
| 14258 |
+
"epoch": 0.024280108730234038,
|
| 14259 |
+
"grad_norm": 1.6046936511993408,
|
| 14260 |
+
"learning_rate": 2.4834390408163324e-05,
|
| 14261 |
+
"loss": 1.7459,
|
| 14262 |
+
"step": 182700
|
| 14263 |
+
},
|
| 14264 |
+
{
|
| 14265 |
+
"epoch": 0.02455919043977696,
|
| 14266 |
+
"grad_norm": 1.572601079940796,
|
| 14267 |
+
"learning_rate": 2.4812250480101693e-05,
|
| 14268 |
+
"loss": 1.7464,
|
| 14269 |
+
"step": 182800
|
| 14270 |
+
},
|
| 14271 |
+
{
|
| 14272 |
+
"epoch": 0.024838272149319877,
|
| 14273 |
+
"grad_norm": 1.5549017190933228,
|
| 14274 |
+
"learning_rate": 2.479011069929603e-05,
|
| 14275 |
+
"loss": 1.7356,
|
| 14276 |
+
"step": 182900
|
| 14277 |
+
},
|
| 14278 |
+
{
|
| 14279 |
+
"epoch": 0.0251173538588628,
|
| 14280 |
+
"grad_norm": 1.5163230895996094,
|
| 14281 |
+
"learning_rate": 2.476797108311106e-05,
|
| 14282 |
+
"loss": 1.7427,
|
| 14283 |
+
"step": 183000
|
| 14284 |
+
},
|
| 14285 |
+
{
|
| 14286 |
+
"epoch": 0.0251173538588628,
|
| 14287 |
+
"eval_loss": 2.1313729286193848,
|
| 14288 |
+
"eval_runtime": 51.744,
|
| 14289 |
+
"eval_samples_per_second": 197.009,
|
| 14290 |
+
"eval_steps_per_second": 1.546,
|
| 14291 |
+
"step": 183000
|
| 14292 |
+
},
|
| 14293 |
+
{
|
| 14294 |
+
"epoch": 0.025396435568405717,
|
| 14295 |
+
"grad_norm": 1.5936397314071655,
|
| 14296 |
+
"learning_rate": 2.474583164891133e-05,
|
| 14297 |
+
"loss": 1.7446,
|
| 14298 |
+
"step": 183100
|
| 14299 |
+
},
|
| 14300 |
+
{
|
| 14301 |
+
"epoch": 0.025675517277948638,
|
| 14302 |
+
"grad_norm": 1.5533971786499023,
|
| 14303 |
+
"learning_rate": 2.4723692414061295e-05,
|
| 14304 |
+
"loss": 1.7452,
|
| 14305 |
+
"step": 183200
|
| 14306 |
+
},
|
| 14307 |
+
{
|
| 14308 |
+
"epoch": 0.025954598987491556,
|
| 14309 |
+
"grad_norm": 1.6152623891830444,
|
| 14310 |
+
"learning_rate": 2.4701553395925214e-05,
|
| 14311 |
+
"loss": 1.7425,
|
| 14312 |
+
"step": 183300
|
| 14313 |
+
},
|
| 14314 |
+
{
|
| 14315 |
+
"epoch": 0.026233680697034478,
|
| 14316 |
+
"grad_norm": 1.4908332824707031,
|
| 14317 |
+
"learning_rate": 2.4679414611867214e-05,
|
| 14318 |
+
"loss": 1.755,
|
| 14319 |
+
"step": 183400
|
| 14320 |
+
},
|
| 14321 |
+
{
|
| 14322 |
+
"epoch": 0.0265127624065774,
|
| 14323 |
+
"grad_norm": 1.6560674905776978,
|
| 14324 |
+
"learning_rate": 2.4657276079251194e-05,
|
| 14325 |
+
"loss": 1.7477,
|
| 14326 |
+
"step": 183500
|
| 14327 |
+
},
|
| 14328 |
+
{
|
| 14329 |
+
"epoch": 0.026791844116120317,
|
| 14330 |
+
"grad_norm": 1.7160277366638184,
|
| 14331 |
+
"learning_rate": 2.4635137815440894e-05,
|
| 14332 |
+
"loss": 1.7446,
|
| 14333 |
+
"step": 183600
|
| 14334 |
+
},
|
| 14335 |
+
{
|
| 14336 |
+
"epoch": 0.02707092582566324,
|
| 14337 |
+
"grad_norm": 1.4447243213653564,
|
| 14338 |
+
"learning_rate": 2.461299983779983e-05,
|
| 14339 |
+
"loss": 1.7403,
|
| 14340 |
+
"step": 183700
|
| 14341 |
+
},
|
| 14342 |
+
{
|
| 14343 |
+
"epoch": 0.027350007535206156,
|
| 14344 |
+
"grad_norm": 1.605068325996399,
|
| 14345 |
+
"learning_rate": 2.459086216369129e-05,
|
| 14346 |
+
"loss": 1.7439,
|
| 14347 |
+
"step": 183800
|
| 14348 |
+
},
|
| 14349 |
+
{
|
| 14350 |
+
"epoch": 0.027629089244749078,
|
| 14351 |
+
"grad_norm": 1.6601132154464722,
|
| 14352 |
+
"learning_rate": 2.4568724810478325e-05,
|
| 14353 |
+
"loss": 1.7439,
|
| 14354 |
+
"step": 183900
|
| 14355 |
+
},
|
| 14356 |
+
{
|
| 14357 |
+
"epoch": 0.027908170954292,
|
| 14358 |
+
"grad_norm": 1.546660304069519,
|
| 14359 |
+
"learning_rate": 2.4546587795523733e-05,
|
| 14360 |
+
"loss": 1.7339,
|
| 14361 |
+
"step": 184000
|
| 14362 |
+
},
|
| 14363 |
+
{
|
| 14364 |
+
"epoch": 0.027908170954292,
|
| 14365 |
+
"eval_loss": 2.1373305320739746,
|
| 14366 |
+
"eval_runtime": 51.7742,
|
| 14367 |
+
"eval_samples_per_second": 196.893,
|
| 14368 |
+
"eval_steps_per_second": 1.545,
|
| 14369 |
+
"step": 184000
|
| 14370 |
+
},
|
| 14371 |
+
{
|
| 14372 |
+
"epoch": 0.00027908170954291995,
|
| 14373 |
+
"grad_norm": 1.6656001806259155,
|
| 14374 |
+
"learning_rate": 2.4524451136190048e-05,
|
| 14375 |
+
"loss": 1.8435,
|
| 14376 |
+
"step": 184100
|
| 14377 |
+
},
|
| 14378 |
+
{
|
| 14379 |
+
"epoch": 0.0005581634190858399,
|
| 14380 |
+
"grad_norm": 1.6392732858657837,
|
| 14381 |
+
"learning_rate": 2.4502314849839546e-05,
|
| 14382 |
+
"loss": 1.8453,
|
| 14383 |
+
"step": 184200
|
| 14384 |
+
},
|
| 14385 |
+
{
|
| 14386 |
+
"epoch": 0.0008372451286287599,
|
| 14387 |
+
"grad_norm": 1.7409366369247437,
|
| 14388 |
+
"learning_rate": 2.4480178953834162e-05,
|
| 14389 |
+
"loss": 1.8407,
|
| 14390 |
+
"step": 184300
|
| 14391 |
+
},
|
| 14392 |
+
{
|
| 14393 |
+
"epoch": 0.0011163268381716798,
|
| 14394 |
+
"grad_norm": 1.5873730182647705,
|
| 14395 |
+
"learning_rate": 2.445804346553557e-05,
|
| 14396 |
+
"loss": 1.8428,
|
| 14397 |
+
"step": 184400
|
| 14398 |
+
},
|
| 14399 |
+
{
|
| 14400 |
+
"epoch": 0.0013954085477146,
|
| 14401 |
+
"grad_norm": 1.5073753595352173,
|
| 14402 |
+
"learning_rate": 2.4435908402305108e-05,
|
| 14403 |
+
"loss": 1.8379,
|
| 14404 |
+
"step": 184500
|
| 14405 |
+
},
|
| 14406 |
+
{
|
| 14407 |
+
"epoch": 0.0016744902572575198,
|
| 14408 |
+
"grad_norm": 2.3680567741394043,
|
| 14409 |
+
"learning_rate": 2.4413773781503788e-05,
|
| 14410 |
+
"loss": 1.83,
|
| 14411 |
+
"step": 184600
|
| 14412 |
+
},
|
| 14413 |
+
{
|
| 14414 |
+
"epoch": 0.00195357196680044,
|
| 14415 |
+
"grad_norm": 1.6823689937591553,
|
| 14416 |
+
"learning_rate": 2.4391639620492243e-05,
|
| 14417 |
+
"loss": 1.8411,
|
| 14418 |
+
"step": 184700
|
| 14419 |
+
},
|
| 14420 |
+
{
|
| 14421 |
+
"epoch": 0.0022326536763433596,
|
| 14422 |
+
"grad_norm": 1.5574064254760742,
|
| 14423 |
+
"learning_rate": 2.4369505936630786e-05,
|
| 14424 |
+
"loss": 1.8351,
|
| 14425 |
+
"step": 184800
|
| 14426 |
+
},
|
| 14427 |
+
{
|
| 14428 |
+
"epoch": 0.0025117353858862797,
|
| 14429 |
+
"grad_norm": 2.146876096725464,
|
| 14430 |
+
"learning_rate": 2.4347372747279337e-05,
|
| 14431 |
+
"loss": 1.833,
|
| 14432 |
+
"step": 184900
|
| 14433 |
+
},
|
| 14434 |
+
{
|
| 14435 |
+
"epoch": 0.0027908170954292,
|
| 14436 |
+
"grad_norm": 1.6746612787246704,
|
| 14437 |
+
"learning_rate": 2.4325240069797438e-05,
|
| 14438 |
+
"loss": 1.8284,
|
| 14439 |
+
"step": 185000
|
| 14440 |
+
},
|
| 14441 |
+
{
|
| 14442 |
+
"epoch": 0.0027908170954292,
|
| 14443 |
+
"eval_loss": 2.133864641189575,
|
| 14444 |
+
"eval_runtime": 52.0009,
|
| 14445 |
+
"eval_samples_per_second": 196.035,
|
| 14446 |
+
"eval_steps_per_second": 1.538,
|
| 14447 |
+
"step": 185000
|
| 14448 |
+
},
|
| 14449 |
+
{
|
| 14450 |
+
"epoch": 0.00306989880497212,
|
| 14451 |
+
"grad_norm": 1.6454411745071411,
|
| 14452 |
+
"learning_rate": 2.430310792154422e-05,
|
| 14453 |
+
"loss": 1.8312,
|
| 14454 |
+
"step": 185100
|
| 14455 |
+
},
|
| 14456 |
+
{
|
| 14457 |
+
"epoch": 0.0033489805145150396,
|
| 14458 |
+
"grad_norm": 1.8907885551452637,
|
| 14459 |
+
"learning_rate": 2.4280976319878392e-05,
|
| 14460 |
+
"loss": 1.8384,
|
| 14461 |
+
"step": 185200
|
| 14462 |
+
},
|
| 14463 |
+
{
|
| 14464 |
+
"epoch": 0.0036280622240579597,
|
| 14465 |
+
"grad_norm": 1.6488444805145264,
|
| 14466 |
+
"learning_rate": 2.425884528215825e-05,
|
| 14467 |
+
"loss": 1.8241,
|
| 14468 |
+
"step": 185300
|
| 14469 |
+
},
|
| 14470 |
+
{
|
| 14471 |
+
"epoch": 0.00390714393360088,
|
| 14472 |
+
"grad_norm": 1.6460552215576172,
|
| 14473 |
+
"learning_rate": 2.423671482574164e-05,
|
| 14474 |
+
"loss": 1.8318,
|
| 14475 |
+
"step": 185400
|
| 14476 |
+
},
|
| 14477 |
+
{
|
| 14478 |
+
"epoch": 0.0041862256431437995,
|
| 14479 |
+
"grad_norm": 1.6229537725448608,
|
| 14480 |
+
"learning_rate": 2.4214584967985962e-05,
|
| 14481 |
+
"loss": 1.8349,
|
| 14482 |
+
"step": 185500
|
| 14483 |
+
},
|
| 14484 |
+
{
|
| 14485 |
+
"epoch": 0.004465307352686719,
|
| 14486 |
+
"grad_norm": 1.5805400609970093,
|
| 14487 |
+
"learning_rate": 2.419245572624812e-05,
|
| 14488 |
+
"loss": 1.823,
|
| 14489 |
+
"step": 185600
|
| 14490 |
+
},
|
| 14491 |
+
{
|
| 14492 |
+
"epoch": 0.00474438906222964,
|
| 14493 |
+
"grad_norm": 1.8274881839752197,
|
| 14494 |
+
"learning_rate": 2.4170327117884562e-05,
|
| 14495 |
+
"loss": 1.8363,
|
| 14496 |
+
"step": 185700
|
| 14497 |
+
},
|
| 14498 |
+
{
|
| 14499 |
+
"epoch": 0.005023470771772559,
|
| 14500 |
+
"grad_norm": 1.5922763347625732,
|
| 14501 |
+
"learning_rate": 2.4148199160251238e-05,
|
| 14502 |
+
"loss": 1.8272,
|
| 14503 |
+
"step": 185800
|
| 14504 |
+
},
|
| 14505 |
+
{
|
| 14506 |
+
"epoch": 0.00530255248131548,
|
| 14507 |
+
"grad_norm": 1.6500530242919922,
|
| 14508 |
+
"learning_rate": 2.4126071870703574e-05,
|
| 14509 |
+
"loss": 1.821,
|
| 14510 |
+
"step": 185900
|
| 14511 |
+
},
|
| 14512 |
+
{
|
| 14513 |
+
"epoch": 0.0055816341908584,
|
| 14514 |
+
"grad_norm": 1.6244685649871826,
|
| 14515 |
+
"learning_rate": 2.410394526659647e-05,
|
| 14516 |
+
"loss": 1.8287,
|
| 14517 |
+
"step": 186000
|
| 14518 |
+
},
|
| 14519 |
+
{
|
| 14520 |
+
"epoch": 0.0055816341908584,
|
| 14521 |
+
"eval_loss": 2.131998300552368,
|
| 14522 |
+
"eval_runtime": 51.5187,
|
| 14523 |
+
"eval_samples_per_second": 197.87,
|
| 14524 |
+
"eval_steps_per_second": 1.553,
|
| 14525 |
+
"step": 186000
|
| 14526 |
}
|
| 14527 |
],
|
| 14528 |
"logging_steps": 100,
|
|
|
|
| 14542 |
"attributes": {}
|
| 14543 |
}
|
| 14544 |
},
|
| 14545 |
+
"total_flos": 1.6232668270166016e+19,
|
| 14546 |
"train_batch_size": 128,
|
| 14547 |
"trial_name": null,
|
| 14548 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5777
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6be0aaef9589a43e4cde380bc3e83ccd55ea3b262dc3f11f0bbc4b35fc934376
|
| 3 |
size 5777
|