Commit
·
6239fb0
1
Parent(s):
f1cb91e
Training in progress, step 200, 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 sha256:9ea4461e42907584114e282e88c9de38cba756a784d54858e76b757a50db92e1
|
| 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 sha256:245a46b5aaaf3d09a5d7b97e6687f31647a91bcd3b123b90d55e67de4369c651
|
| 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 sha256:240e3a8e970dcbee6d18efecf031ae0a13a4a18d6100321e85ed97bbfb203f8a
|
| 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:e5b53e8445e85a4e0deee09cd395d9a75da0ef05192cd139529507aa8b8c86c4
|
| 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 sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
|
| 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,
|
|
@@ -49,13 +49,19 @@
|
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
"loss": 1.1292,
|
| 51 |
"step": 175
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
}
|
| 53 |
],
|
| 54 |
"logging_steps": 25,
|
| 55 |
"max_steps": 728,
|
| 56 |
"num_train_epochs": 1,
|
| 57 |
"save_steps": 25,
|
| 58 |
-
"total_flos":
|
| 59 |
"trial_name": null,
|
| 60 |
"trial_params": null
|
| 61 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.27472527472527475,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
"loss": 1.1292,
|
| 51 |
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.27,
|
| 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": 1928196829937664.0,
|
| 65 |
"trial_name": null,
|
| 66 |
"trial_params": null
|
| 67 |
}
|