Commit ·
32702df
1
Parent(s): d577c26
Training in progress, step 170
Browse files
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 522284877
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b731b33a663df9b5d325ea24811ab15b363e54445aff4ec4bd6fe507e6467d7
|
| 3 |
size 522284877
|
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 522284877
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b731b33a663df9b5d325ea24811ab15b363e54445aff4ec4bd6fe507e6467d7
|
| 3 |
size 522284877
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1044539653
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51b0f686c1f2bee0e68037a4cca40921cdb05f7528cabced5713e8ae0cb43297
|
| 3 |
size 1044539653
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb77c5432001f75ca5c8c8d2df598ea67c727a71f0a1359228917568a1d0916
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3841b7d3094f97af299f97dddaa8fe1e5f1142ed0601dee132ea7f776f6ffff
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -102,11 +102,17 @@
|
|
| 102 |
"learning_rate": 0.0002,
|
| 103 |
"loss": 0.009,
|
| 104 |
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
}
|
| 106 |
],
|
| 107 |
"max_steps": 200,
|
| 108 |
"num_train_epochs": 50,
|
| 109 |
-
"total_flos": 5.
|
| 110 |
"trial_name": null,
|
| 111 |
"trial_params": null
|
| 112 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 42.5,
|
| 5 |
+
"global_step": 170,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 102 |
"learning_rate": 0.0002,
|
| 103 |
"loss": 0.009,
|
| 104 |
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 42.5,
|
| 108 |
+
"learning_rate": 0.0002,
|
| 109 |
+
"loss": 0.0088,
|
| 110 |
+
"step": 170
|
| 111 |
}
|
| 112 |
],
|
| 113 |
"max_steps": 200,
|
| 114 |
"num_train_epochs": 50,
|
| 115 |
+
"total_flos": 5.558694508363776e+16,
|
| 116 |
"trial_name": null,
|
| 117 |
"trial_params": null
|
| 118 |
}
|