Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1131 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 75702552
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a575f48324f22cec4c8f4faa33bdde9382652cb3b3aec77c2bbe6250e28edbe7
|
| 3 |
size 75702552
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:889605b1755314f11b8105567b34ff099ce9a513411f21f8f14d541edbbedaff
|
| 3 |
+
size 151452026
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b6350a187860164bf0e9942ab3e0e4566cdd378c660b6e7ad816657f9630b76
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9776462505945146,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 18500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.976206841854809e-05,
|
| 14 |
+
"loss": 1.337,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4.949769999471263e-05,
|
| 20 |
+
"loss": 1.2993,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 4.923333157087718e-05,
|
| 26 |
+
"loss": 1.2719,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 4.896896314704172e-05,
|
| 32 |
+
"loss": 1.2761,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 4.870459472320626e-05,
|
| 38 |
+
"loss": 1.271,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 4.844022629937081e-05,
|
| 44 |
+
"loss": 1.2504,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 4.8175857875535345e-05,
|
| 50 |
+
"loss": 1.254,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 4.791148945169989e-05,
|
| 56 |
+
"loss": 1.2508,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"learning_rate": 4.7647121027864434e-05,
|
| 62 |
+
"loss": 1.2614,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 4.738275260402898e-05,
|
| 68 |
+
"loss": 1.2447,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 4.711838418019352e-05,
|
| 74 |
+
"loss": 1.2606,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 4.685401575635806e-05,
|
| 80 |
+
"loss": 1.2447,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 4.6589647332522605e-05,
|
| 86 |
+
"loss": 1.2565,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 4.632527890868715e-05,
|
| 92 |
+
"loss": 1.258,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08,
|
| 97 |
+
"learning_rate": 4.6060910484851693e-05,
|
| 98 |
+
"loss": 1.255,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 4.579654206101623e-05,
|
| 104 |
+
"loss": 1.2449,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.09,
|
| 109 |
+
"learning_rate": 4.5532173637180775e-05,
|
| 110 |
+
"loss": 1.258,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.1,
|
| 115 |
+
"learning_rate": 4.526780521334532e-05,
|
| 116 |
+
"loss": 1.2365,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1,
|
| 121 |
+
"learning_rate": 4.5003436789509864e-05,
|
| 122 |
+
"loss": 1.2506,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.11,
|
| 127 |
+
"learning_rate": 4.473906836567441e-05,
|
| 128 |
+
"loss": 1.2561,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.11,
|
| 133 |
+
"learning_rate": 4.4474699941838946e-05,
|
| 134 |
+
"loss": 1.2538,
|
| 135 |
+
"step": 2100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12,
|
| 139 |
+
"learning_rate": 4.421033151800349e-05,
|
| 140 |
+
"loss": 1.2522,
|
| 141 |
+
"step": 2200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.12,
|
| 145 |
+
"learning_rate": 4.3945963094168035e-05,
|
| 146 |
+
"loss": 1.2524,
|
| 147 |
+
"step": 2300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.13,
|
| 151 |
+
"learning_rate": 4.368159467033257e-05,
|
| 152 |
+
"loss": 1.2464,
|
| 153 |
+
"step": 2400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.13,
|
| 157 |
+
"learning_rate": 4.3417226246497124e-05,
|
| 158 |
+
"loss": 1.2514,
|
| 159 |
+
"step": 2500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.14,
|
| 163 |
+
"learning_rate": 4.315285782266166e-05,
|
| 164 |
+
"loss": 1.2429,
|
| 165 |
+
"step": 2600
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.14,
|
| 169 |
+
"learning_rate": 4.2888489398826206e-05,
|
| 170 |
+
"loss": 1.2481,
|
| 171 |
+
"step": 2700
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.15,
|
| 175 |
+
"learning_rate": 4.262412097499075e-05,
|
| 176 |
+
"loss": 1.242,
|
| 177 |
+
"step": 2800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15,
|
| 181 |
+
"learning_rate": 4.235975255115529e-05,
|
| 182 |
+
"loss": 1.2489,
|
| 183 |
+
"step": 2900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.16,
|
| 187 |
+
"learning_rate": 4.209538412731984e-05,
|
| 188 |
+
"loss": 1.236,
|
| 189 |
+
"step": 3000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16,
|
| 193 |
+
"learning_rate": 4.183101570348438e-05,
|
| 194 |
+
"loss": 1.2447,
|
| 195 |
+
"step": 3100
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 4.1566647279648915e-05,
|
| 200 |
+
"loss": 1.2449,
|
| 201 |
+
"step": 3200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.17,
|
| 205 |
+
"learning_rate": 4.1302278855813466e-05,
|
| 206 |
+
"loss": 1.2452,
|
| 207 |
+
"step": 3300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.18,
|
| 211 |
+
"learning_rate": 4.1037910431978004e-05,
|
| 212 |
+
"loss": 1.2367,
|
| 213 |
+
"step": 3400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.18,
|
| 217 |
+
"learning_rate": 4.077354200814255e-05,
|
| 218 |
+
"loss": 1.2414,
|
| 219 |
+
"step": 3500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19,
|
| 223 |
+
"learning_rate": 4.050917358430709e-05,
|
| 224 |
+
"loss": 1.2377,
|
| 225 |
+
"step": 3600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.2,
|
| 229 |
+
"learning_rate": 4.024480516047163e-05,
|
| 230 |
+
"loss": 1.2365,
|
| 231 |
+
"step": 3700
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.2,
|
| 235 |
+
"learning_rate": 3.998043673663618e-05,
|
| 236 |
+
"loss": 1.2461,
|
| 237 |
+
"step": 3800
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.21,
|
| 241 |
+
"learning_rate": 3.971606831280072e-05,
|
| 242 |
+
"loss": 1.2499,
|
| 243 |
+
"step": 3900
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.21,
|
| 247 |
+
"learning_rate": 3.9451699888965264e-05,
|
| 248 |
+
"loss": 1.2328,
|
| 249 |
+
"step": 4000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.22,
|
| 253 |
+
"learning_rate": 3.918733146512981e-05,
|
| 254 |
+
"loss": 1.2347,
|
| 255 |
+
"step": 4100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.22,
|
| 259 |
+
"learning_rate": 3.8922963041294346e-05,
|
| 260 |
+
"loss": 1.2482,
|
| 261 |
+
"step": 4200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.23,
|
| 265 |
+
"learning_rate": 3.865859461745889e-05,
|
| 266 |
+
"loss": 1.2127,
|
| 267 |
+
"step": 4300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.23,
|
| 271 |
+
"learning_rate": 3.8394226193623434e-05,
|
| 272 |
+
"loss": 1.2296,
|
| 273 |
+
"step": 4400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.24,
|
| 277 |
+
"learning_rate": 3.812985776978798e-05,
|
| 278 |
+
"loss": 1.2314,
|
| 279 |
+
"step": 4500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.24,
|
| 283 |
+
"learning_rate": 3.786548934595252e-05,
|
| 284 |
+
"loss": 1.2111,
|
| 285 |
+
"step": 4600
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 3.760112092211707e-05,
|
| 290 |
+
"loss": 1.2312,
|
| 291 |
+
"step": 4700
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.25,
|
| 295 |
+
"learning_rate": 3.7336752498281605e-05,
|
| 296 |
+
"loss": 1.2291,
|
| 297 |
+
"step": 4800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.26,
|
| 301 |
+
"learning_rate": 3.707238407444615e-05,
|
| 302 |
+
"loss": 1.2356,
|
| 303 |
+
"step": 4900
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.26,
|
| 307 |
+
"learning_rate": 3.6808015650610694e-05,
|
| 308 |
+
"loss": 1.2411,
|
| 309 |
+
"step": 5000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.27,
|
| 313 |
+
"learning_rate": 3.654364722677523e-05,
|
| 314 |
+
"loss": 1.228,
|
| 315 |
+
"step": 5100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.27,
|
| 319 |
+
"learning_rate": 3.627927880293978e-05,
|
| 320 |
+
"loss": 1.2384,
|
| 321 |
+
"step": 5200
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.28,
|
| 325 |
+
"learning_rate": 3.601491037910432e-05,
|
| 326 |
+
"loss": 1.231,
|
| 327 |
+
"step": 5300
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.29,
|
| 331 |
+
"learning_rate": 3.5750541955268865e-05,
|
| 332 |
+
"loss": 1.2378,
|
| 333 |
+
"step": 5400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.29,
|
| 337 |
+
"learning_rate": 3.548617353143341e-05,
|
| 338 |
+
"loss": 1.2366,
|
| 339 |
+
"step": 5500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3,
|
| 343 |
+
"learning_rate": 3.522180510759795e-05,
|
| 344 |
+
"loss": 1.2356,
|
| 345 |
+
"step": 5600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3,
|
| 349 |
+
"learning_rate": 3.49574366837625e-05,
|
| 350 |
+
"loss": 1.2266,
|
| 351 |
+
"step": 5700
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.31,
|
| 355 |
+
"learning_rate": 3.4693068259927036e-05,
|
| 356 |
+
"loss": 1.2385,
|
| 357 |
+
"step": 5800
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.31,
|
| 361 |
+
"learning_rate": 3.4428699836091574e-05,
|
| 362 |
+
"loss": 1.2307,
|
| 363 |
+
"step": 5900
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.32,
|
| 367 |
+
"learning_rate": 3.4164331412256125e-05,
|
| 368 |
+
"loss": 1.2245,
|
| 369 |
+
"step": 6000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.32,
|
| 373 |
+
"learning_rate": 3.389996298842066e-05,
|
| 374 |
+
"loss": 1.2311,
|
| 375 |
+
"step": 6100
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.33,
|
| 379 |
+
"learning_rate": 3.363559456458521e-05,
|
| 380 |
+
"loss": 1.2214,
|
| 381 |
+
"step": 6200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.33,
|
| 385 |
+
"learning_rate": 3.337122614074975e-05,
|
| 386 |
+
"loss": 1.2196,
|
| 387 |
+
"step": 6300
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.34,
|
| 391 |
+
"learning_rate": 3.310685771691429e-05,
|
| 392 |
+
"loss": 1.2319,
|
| 393 |
+
"step": 6400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.34,
|
| 397 |
+
"learning_rate": 3.284248929307884e-05,
|
| 398 |
+
"loss": 1.2291,
|
| 399 |
+
"step": 6500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.35,
|
| 403 |
+
"learning_rate": 3.257812086924338e-05,
|
| 404 |
+
"loss": 1.2245,
|
| 405 |
+
"step": 6600
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.35,
|
| 409 |
+
"learning_rate": 3.231375244540792e-05,
|
| 410 |
+
"loss": 1.2134,
|
| 411 |
+
"step": 6700
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.36,
|
| 415 |
+
"learning_rate": 3.204938402157247e-05,
|
| 416 |
+
"loss": 1.2256,
|
| 417 |
+
"step": 6800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.36,
|
| 421 |
+
"learning_rate": 3.1785015597737005e-05,
|
| 422 |
+
"loss": 1.2235,
|
| 423 |
+
"step": 6900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.37,
|
| 427 |
+
"learning_rate": 3.152064717390155e-05,
|
| 428 |
+
"loss": 1.2269,
|
| 429 |
+
"step": 7000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.38,
|
| 433 |
+
"learning_rate": 3.1256278750066093e-05,
|
| 434 |
+
"loss": 1.2315,
|
| 435 |
+
"step": 7100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.38,
|
| 439 |
+
"learning_rate": 3.099191032623064e-05,
|
| 440 |
+
"loss": 1.2325,
|
| 441 |
+
"step": 7200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.39,
|
| 445 |
+
"learning_rate": 3.072754190239518e-05,
|
| 446 |
+
"loss": 1.2165,
|
| 447 |
+
"step": 7300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.39,
|
| 451 |
+
"learning_rate": 3.046317347855972e-05,
|
| 452 |
+
"loss": 1.2287,
|
| 453 |
+
"step": 7400
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.4,
|
| 457 |
+
"learning_rate": 3.0198805054724268e-05,
|
| 458 |
+
"loss": 1.2265,
|
| 459 |
+
"step": 7500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.4,
|
| 463 |
+
"learning_rate": 2.9934436630888805e-05,
|
| 464 |
+
"loss": 1.224,
|
| 465 |
+
"step": 7600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.41,
|
| 469 |
+
"learning_rate": 2.9670068207053353e-05,
|
| 470 |
+
"loss": 1.217,
|
| 471 |
+
"step": 7700
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.41,
|
| 475 |
+
"learning_rate": 2.9405699783217894e-05,
|
| 476 |
+
"loss": 1.2181,
|
| 477 |
+
"step": 7800
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.42,
|
| 481 |
+
"learning_rate": 2.9141331359382435e-05,
|
| 482 |
+
"loss": 1.2297,
|
| 483 |
+
"step": 7900
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.42,
|
| 487 |
+
"learning_rate": 2.887696293554698e-05,
|
| 488 |
+
"loss": 1.2222,
|
| 489 |
+
"step": 8000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.43,
|
| 493 |
+
"learning_rate": 2.861259451171152e-05,
|
| 494 |
+
"loss": 1.2058,
|
| 495 |
+
"step": 8100
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.43,
|
| 499 |
+
"learning_rate": 2.834822608787607e-05,
|
| 500 |
+
"loss": 1.2119,
|
| 501 |
+
"step": 8200
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.44,
|
| 505 |
+
"learning_rate": 2.8086501348278964e-05,
|
| 506 |
+
"loss": 1.2316,
|
| 507 |
+
"step": 8300
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.44,
|
| 511 |
+
"learning_rate": 2.7822132924443505e-05,
|
| 512 |
+
"loss": 1.2241,
|
| 513 |
+
"step": 8400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.45,
|
| 517 |
+
"learning_rate": 2.7557764500608046e-05,
|
| 518 |
+
"loss": 1.2189,
|
| 519 |
+
"step": 8500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.45,
|
| 523 |
+
"learning_rate": 2.7293396076772594e-05,
|
| 524 |
+
"loss": 1.2146,
|
| 525 |
+
"step": 8600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.46,
|
| 529 |
+
"learning_rate": 2.702902765293713e-05,
|
| 530 |
+
"loss": 1.2106,
|
| 531 |
+
"step": 8700
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.47,
|
| 535 |
+
"learning_rate": 2.676465922910168e-05,
|
| 536 |
+
"loss": 1.2073,
|
| 537 |
+
"step": 8800
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.47,
|
| 541 |
+
"learning_rate": 2.650029080526622e-05,
|
| 542 |
+
"loss": 1.2197,
|
| 543 |
+
"step": 8900
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.48,
|
| 547 |
+
"learning_rate": 2.623592238143076e-05,
|
| 548 |
+
"loss": 1.221,
|
| 549 |
+
"step": 9000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.48,
|
| 553 |
+
"learning_rate": 2.5971553957595306e-05,
|
| 554 |
+
"loss": 1.2239,
|
| 555 |
+
"step": 9100
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.49,
|
| 559 |
+
"learning_rate": 2.5707185533759847e-05,
|
| 560 |
+
"loss": 1.2224,
|
| 561 |
+
"step": 9200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.49,
|
| 565 |
+
"learning_rate": 2.5442817109924395e-05,
|
| 566 |
+
"loss": 1.2312,
|
| 567 |
+
"step": 9300
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.5,
|
| 571 |
+
"learning_rate": 2.5178448686088936e-05,
|
| 572 |
+
"loss": 1.2248,
|
| 573 |
+
"step": 9400
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.5,
|
| 577 |
+
"learning_rate": 2.4914080262253477e-05,
|
| 578 |
+
"loss": 1.2197,
|
| 579 |
+
"step": 9500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.51,
|
| 583 |
+
"learning_rate": 2.464971183841802e-05,
|
| 584 |
+
"loss": 1.2362,
|
| 585 |
+
"step": 9600
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.51,
|
| 589 |
+
"learning_rate": 2.4385343414582562e-05,
|
| 590 |
+
"loss": 1.2029,
|
| 591 |
+
"step": 9700
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.52,
|
| 595 |
+
"learning_rate": 2.4120974990747107e-05,
|
| 596 |
+
"loss": 1.2212,
|
| 597 |
+
"step": 9800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.52,
|
| 601 |
+
"learning_rate": 2.3856606566911648e-05,
|
| 602 |
+
"loss": 1.2217,
|
| 603 |
+
"step": 9900
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.53,
|
| 607 |
+
"learning_rate": 2.3592238143076192e-05,
|
| 608 |
+
"loss": 1.2089,
|
| 609 |
+
"step": 10000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.53,
|
| 613 |
+
"learning_rate": 2.3327869719240737e-05,
|
| 614 |
+
"loss": 1.2174,
|
| 615 |
+
"step": 10100
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.54,
|
| 619 |
+
"learning_rate": 2.3063501295405278e-05,
|
| 620 |
+
"loss": 1.2269,
|
| 621 |
+
"step": 10200
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.54,
|
| 625 |
+
"learning_rate": 2.2801776555808173e-05,
|
| 626 |
+
"loss": 1.2177,
|
| 627 |
+
"step": 10300
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.55,
|
| 631 |
+
"learning_rate": 2.2537408131972718e-05,
|
| 632 |
+
"loss": 1.23,
|
| 633 |
+
"step": 10400
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.55,
|
| 637 |
+
"learning_rate": 2.2273039708137262e-05,
|
| 638 |
+
"loss": 1.2235,
|
| 639 |
+
"step": 10500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.56,
|
| 643 |
+
"learning_rate": 2.2008671284301803e-05,
|
| 644 |
+
"loss": 1.2291,
|
| 645 |
+
"step": 10600
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.57,
|
| 649 |
+
"learning_rate": 2.1744302860466348e-05,
|
| 650 |
+
"loss": 1.2199,
|
| 651 |
+
"step": 10700
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.57,
|
| 655 |
+
"learning_rate": 2.147993443663089e-05,
|
| 656 |
+
"loss": 1.2101,
|
| 657 |
+
"step": 10800
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.58,
|
| 661 |
+
"learning_rate": 2.1215566012795433e-05,
|
| 662 |
+
"loss": 1.2239,
|
| 663 |
+
"step": 10900
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.58,
|
| 667 |
+
"learning_rate": 2.0951197588959974e-05,
|
| 668 |
+
"loss": 1.2105,
|
| 669 |
+
"step": 11000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.59,
|
| 673 |
+
"learning_rate": 2.068682916512452e-05,
|
| 674 |
+
"loss": 1.2249,
|
| 675 |
+
"step": 11100
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.59,
|
| 679 |
+
"learning_rate": 2.0422460741289063e-05,
|
| 680 |
+
"loss": 1.2032,
|
| 681 |
+
"step": 11200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6,
|
| 685 |
+
"learning_rate": 2.0158092317453604e-05,
|
| 686 |
+
"loss": 1.2297,
|
| 687 |
+
"step": 11300
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.6,
|
| 691 |
+
"learning_rate": 1.9893723893618145e-05,
|
| 692 |
+
"loss": 1.2161,
|
| 693 |
+
"step": 11400
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.61,
|
| 697 |
+
"learning_rate": 1.962935546978269e-05,
|
| 698 |
+
"loss": 1.2199,
|
| 699 |
+
"step": 11500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.61,
|
| 703 |
+
"learning_rate": 1.9364987045947234e-05,
|
| 704 |
+
"loss": 1.2221,
|
| 705 |
+
"step": 11600
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.62,
|
| 709 |
+
"learning_rate": 1.9100618622111775e-05,
|
| 710 |
+
"loss": 1.2171,
|
| 711 |
+
"step": 11700
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.62,
|
| 715 |
+
"learning_rate": 1.883625019827632e-05,
|
| 716 |
+
"loss": 1.2129,
|
| 717 |
+
"step": 11800
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.63,
|
| 721 |
+
"learning_rate": 1.857188177444086e-05,
|
| 722 |
+
"loss": 1.2165,
|
| 723 |
+
"step": 11900
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.63,
|
| 727 |
+
"learning_rate": 1.8307513350605405e-05,
|
| 728 |
+
"loss": 1.2229,
|
| 729 |
+
"step": 12000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.64,
|
| 733 |
+
"learning_rate": 1.8043144926769946e-05,
|
| 734 |
+
"loss": 1.2186,
|
| 735 |
+
"step": 12100
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.64,
|
| 739 |
+
"learning_rate": 1.777877650293449e-05,
|
| 740 |
+
"loss": 1.2142,
|
| 741 |
+
"step": 12200
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.65,
|
| 745 |
+
"learning_rate": 1.7514408079099035e-05,
|
| 746 |
+
"loss": 1.207,
|
| 747 |
+
"step": 12300
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.66,
|
| 751 |
+
"learning_rate": 1.7250039655263576e-05,
|
| 752 |
+
"loss": 1.2164,
|
| 753 |
+
"step": 12400
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.66,
|
| 757 |
+
"learning_rate": 1.6985671231428117e-05,
|
| 758 |
+
"loss": 1.2245,
|
| 759 |
+
"step": 12500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.67,
|
| 763 |
+
"learning_rate": 1.672130280759266e-05,
|
| 764 |
+
"loss": 1.2131,
|
| 765 |
+
"step": 12600
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.67,
|
| 769 |
+
"learning_rate": 1.645957806799556e-05,
|
| 770 |
+
"loss": 1.2144,
|
| 771 |
+
"step": 12700
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.68,
|
| 775 |
+
"learning_rate": 1.6195209644160105e-05,
|
| 776 |
+
"loss": 1.22,
|
| 777 |
+
"step": 12800
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.68,
|
| 781 |
+
"learning_rate": 1.5930841220324646e-05,
|
| 782 |
+
"loss": 1.2168,
|
| 783 |
+
"step": 12900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.69,
|
| 787 |
+
"learning_rate": 1.5666472796489187e-05,
|
| 788 |
+
"loss": 1.2251,
|
| 789 |
+
"step": 13000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.69,
|
| 793 |
+
"learning_rate": 1.540210437265373e-05,
|
| 794 |
+
"loss": 1.2185,
|
| 795 |
+
"step": 13100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.7,
|
| 799 |
+
"learning_rate": 1.5137735948818274e-05,
|
| 800 |
+
"loss": 1.2222,
|
| 801 |
+
"step": 13200
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.7,
|
| 805 |
+
"learning_rate": 1.4873367524982817e-05,
|
| 806 |
+
"loss": 1.1998,
|
| 807 |
+
"step": 13300
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.71,
|
| 811 |
+
"learning_rate": 1.4608999101147361e-05,
|
| 812 |
+
"loss": 1.2237,
|
| 813 |
+
"step": 13400
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.71,
|
| 817 |
+
"learning_rate": 1.4344630677311902e-05,
|
| 818 |
+
"loss": 1.2265,
|
| 819 |
+
"step": 13500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.72,
|
| 823 |
+
"learning_rate": 1.4080262253476445e-05,
|
| 824 |
+
"loss": 1.2253,
|
| 825 |
+
"step": 13600
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.72,
|
| 829 |
+
"learning_rate": 1.3815893829640988e-05,
|
| 830 |
+
"loss": 1.2144,
|
| 831 |
+
"step": 13700
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.73,
|
| 835 |
+
"learning_rate": 1.3551525405805532e-05,
|
| 836 |
+
"loss": 1.2199,
|
| 837 |
+
"step": 13800
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.73,
|
| 841 |
+
"learning_rate": 1.3287156981970075e-05,
|
| 842 |
+
"loss": 1.2057,
|
| 843 |
+
"step": 13900
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.74,
|
| 847 |
+
"learning_rate": 1.3022788558134616e-05,
|
| 848 |
+
"loss": 1.2192,
|
| 849 |
+
"step": 14000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.75,
|
| 853 |
+
"learning_rate": 1.2758420134299159e-05,
|
| 854 |
+
"loss": 1.231,
|
| 855 |
+
"step": 14100
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.75,
|
| 859 |
+
"learning_rate": 1.2494051710463703e-05,
|
| 860 |
+
"loss": 1.2189,
|
| 861 |
+
"step": 14200
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.76,
|
| 865 |
+
"learning_rate": 1.2229683286628246e-05,
|
| 866 |
+
"loss": 1.2234,
|
| 867 |
+
"step": 14300
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.76,
|
| 871 |
+
"learning_rate": 1.1965314862792788e-05,
|
| 872 |
+
"loss": 1.2117,
|
| 873 |
+
"step": 14400
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.77,
|
| 877 |
+
"learning_rate": 1.1700946438957331e-05,
|
| 878 |
+
"loss": 1.2118,
|
| 879 |
+
"step": 14500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.77,
|
| 883 |
+
"learning_rate": 1.1436578015121874e-05,
|
| 884 |
+
"loss": 1.2267,
|
| 885 |
+
"step": 14600
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.78,
|
| 889 |
+
"learning_rate": 1.1172209591286417e-05,
|
| 890 |
+
"loss": 1.2286,
|
| 891 |
+
"step": 14700
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.78,
|
| 895 |
+
"learning_rate": 1.0907841167450961e-05,
|
| 896 |
+
"loss": 1.2125,
|
| 897 |
+
"step": 14800
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.79,
|
| 901 |
+
"learning_rate": 1.0643472743615502e-05,
|
| 902 |
+
"loss": 1.2132,
|
| 903 |
+
"step": 14900
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.79,
|
| 907 |
+
"learning_rate": 1.0379104319780047e-05,
|
| 908 |
+
"loss": 1.2215,
|
| 909 |
+
"step": 15000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8,
|
| 913 |
+
"learning_rate": 1.011473589594459e-05,
|
| 914 |
+
"loss": 1.2182,
|
| 915 |
+
"step": 15100
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.8,
|
| 919 |
+
"learning_rate": 9.850367472109132e-06,
|
| 920 |
+
"loss": 1.2192,
|
| 921 |
+
"step": 15200
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.81,
|
| 925 |
+
"learning_rate": 9.585999048273675e-06,
|
| 926 |
+
"loss": 1.2185,
|
| 927 |
+
"step": 15300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.81,
|
| 931 |
+
"learning_rate": 9.321630624438218e-06,
|
| 932 |
+
"loss": 1.2298,
|
| 933 |
+
"step": 15400
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.82,
|
| 937 |
+
"learning_rate": 9.05726220060276e-06,
|
| 938 |
+
"loss": 1.2297,
|
| 939 |
+
"step": 15500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.82,
|
| 943 |
+
"learning_rate": 8.792893776767305e-06,
|
| 944 |
+
"loss": 1.2076,
|
| 945 |
+
"step": 15600
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.83,
|
| 949 |
+
"learning_rate": 8.528525352931846e-06,
|
| 950 |
+
"loss": 1.2244,
|
| 951 |
+
"step": 15700
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.83,
|
| 955 |
+
"learning_rate": 8.26415692909639e-06,
|
| 956 |
+
"loss": 1.2168,
|
| 957 |
+
"step": 15800
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.84,
|
| 961 |
+
"learning_rate": 8.002432189499287e-06,
|
| 962 |
+
"loss": 1.2245,
|
| 963 |
+
"step": 15900
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.85,
|
| 967 |
+
"learning_rate": 7.738063765663828e-06,
|
| 968 |
+
"loss": 1.2088,
|
| 969 |
+
"step": 16000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.85,
|
| 973 |
+
"learning_rate": 7.473695341828373e-06,
|
| 974 |
+
"loss": 1.2214,
|
| 975 |
+
"step": 16100
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.86,
|
| 979 |
+
"learning_rate": 7.209326917992915e-06,
|
| 980 |
+
"loss": 1.2149,
|
| 981 |
+
"step": 16200
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.86,
|
| 985 |
+
"learning_rate": 6.944958494157458e-06,
|
| 986 |
+
"loss": 1.2143,
|
| 987 |
+
"step": 16300
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.87,
|
| 991 |
+
"learning_rate": 6.680590070322001e-06,
|
| 992 |
+
"loss": 1.2175,
|
| 993 |
+
"step": 16400
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.87,
|
| 997 |
+
"learning_rate": 6.416221646486544e-06,
|
| 998 |
+
"loss": 1.2132,
|
| 999 |
+
"step": 16500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.88,
|
| 1003 |
+
"learning_rate": 6.1518532226510865e-06,
|
| 1004 |
+
"loss": 1.2299,
|
| 1005 |
+
"step": 16600
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.88,
|
| 1009 |
+
"learning_rate": 5.887484798815629e-06,
|
| 1010 |
+
"loss": 1.2156,
|
| 1011 |
+
"step": 16700
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.89,
|
| 1015 |
+
"learning_rate": 5.623116374980172e-06,
|
| 1016 |
+
"loss": 1.2037,
|
| 1017 |
+
"step": 16800
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.89,
|
| 1021 |
+
"learning_rate": 5.358747951144716e-06,
|
| 1022 |
+
"loss": 1.2134,
|
| 1023 |
+
"step": 16900
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.9,
|
| 1027 |
+
"learning_rate": 5.094379527309258e-06,
|
| 1028 |
+
"loss": 1.2253,
|
| 1029 |
+
"step": 17000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.9,
|
| 1033 |
+
"learning_rate": 4.830011103473801e-06,
|
| 1034 |
+
"loss": 1.2136,
|
| 1035 |
+
"step": 17100
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.91,
|
| 1039 |
+
"learning_rate": 4.565642679638344e-06,
|
| 1040 |
+
"loss": 1.2039,
|
| 1041 |
+
"step": 17200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.91,
|
| 1045 |
+
"learning_rate": 4.3012742558028865e-06,
|
| 1046 |
+
"loss": 1.2187,
|
| 1047 |
+
"step": 17300
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.92,
|
| 1051 |
+
"learning_rate": 4.03690583196743e-06,
|
| 1052 |
+
"loss": 1.2113,
|
| 1053 |
+
"step": 17400
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.92,
|
| 1057 |
+
"learning_rate": 3.772537408131973e-06,
|
| 1058 |
+
"loss": 1.2124,
|
| 1059 |
+
"step": 17500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.93,
|
| 1063 |
+
"learning_rate": 3.5081689842965156e-06,
|
| 1064 |
+
"loss": 1.215,
|
| 1065 |
+
"step": 17600
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.94,
|
| 1069 |
+
"learning_rate": 3.2438005604610583e-06,
|
| 1070 |
+
"loss": 1.2161,
|
| 1071 |
+
"step": 17700
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.94,
|
| 1075 |
+
"learning_rate": 2.9794321366256015e-06,
|
| 1076 |
+
"loss": 1.224,
|
| 1077 |
+
"step": 17800
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.95,
|
| 1081 |
+
"learning_rate": 2.7150637127901447e-06,
|
| 1082 |
+
"loss": 1.2201,
|
| 1083 |
+
"step": 17900
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.95,
|
| 1087 |
+
"learning_rate": 2.4506952889546874e-06,
|
| 1088 |
+
"loss": 1.2173,
|
| 1089 |
+
"step": 18000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.96,
|
| 1093 |
+
"learning_rate": 2.1863268651192306e-06,
|
| 1094 |
+
"loss": 1.2074,
|
| 1095 |
+
"step": 18100
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.96,
|
| 1099 |
+
"learning_rate": 1.9219584412837733e-06,
|
| 1100 |
+
"loss": 1.2178,
|
| 1101 |
+
"step": 18200
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.97,
|
| 1105 |
+
"learning_rate": 1.6575900174483158e-06,
|
| 1106 |
+
"loss": 1.2064,
|
| 1107 |
+
"step": 18300
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.97,
|
| 1111 |
+
"learning_rate": 1.393221593612859e-06,
|
| 1112 |
+
"loss": 1.2258,
|
| 1113 |
+
"step": 18400
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.98,
|
| 1117 |
+
"learning_rate": 1.128853169777402e-06,
|
| 1118 |
+
"loss": 1.2236,
|
| 1119 |
+
"step": 18500
|
| 1120 |
+
}
|
| 1121 |
+
],
|
| 1122 |
+
"logging_steps": 100,
|
| 1123 |
+
"max_steps": 18923,
|
| 1124 |
+
"num_input_tokens_seen": 0,
|
| 1125 |
+
"num_train_epochs": 1,
|
| 1126 |
+
"save_steps": 500,
|
| 1127 |
+
"total_flos": 6.451372228608e+16,
|
| 1128 |
+
"train_batch_size": 10,
|
| 1129 |
+
"trial_name": null,
|
| 1130 |
+
"trial_params": null
|
| 1131 |
+
}
|