Commit
·
2d5707a
1
Parent(s):
7b01e24
Training in progress, step 225, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369214349
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f6170342b584389e5a7190975db4df76f7b3d540141cf7107af6f307e2faafd
|
| 3 |
size 369214349
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369142184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5abffc3dbbd44dfacd796c08ec5504239ba0e3ca3bb61665b9b8a0c5ddf9a986
|
| 3 |
size 369142184
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738393541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:100707782cd473aa3b38af8132255da4059b88c7ff7b15da4e8f8ca867347e6c
|
| 3 |
size 738393541
|
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 sha256:39a1cd5c8d33ebe8203b51b1340c8b6b6c6b1c6ea9f466533558c981adbeb460
|
| 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 sha256:4cfc2bc1e4199a1fa7f527cb78be2016115dbd7e0ba477b92d6f1060ea1c01b8
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -55,13 +55,19 @@
|
|
| 55 |
"learning_rate": 0.0002,
|
| 56 |
"loss": 0.8171,
|
| 57 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
}
|
| 59 |
],
|
| 60 |
"logging_steps": 25,
|
| 61 |
"max_steps": 728,
|
| 62 |
"num_train_epochs": 1,
|
| 63 |
"save_steps": 25,
|
| 64 |
-
"total_flos":
|
| 65 |
"trial_name": null,
|
| 66 |
"trial_params": null
|
| 67 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3090659340659341,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 225,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 55 |
"learning_rate": 0.0002,
|
| 56 |
"loss": 0.8171,
|
| 57 |
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.31,
|
| 61 |
+
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 1.1259,
|
| 63 |
+
"step": 225
|
| 64 |
}
|
| 65 |
],
|
| 66 |
"logging_steps": 25,
|
| 67 |
"max_steps": 728,
|
| 68 |
"num_train_epochs": 1,
|
| 69 |
"save_steps": 25,
|
| 70 |
+
"total_flos": 2237634908258304.0,
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|
| 73 |
}
|