Commit
·
7fa835a
1
Parent(s):
7b491b3
Training in progress, step 75, 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:fab8dd093ffd578070f91237acd84feec8bca27930a5ddff94863fae27f76e3d
|
| 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 sha256:01304c9860635d04ae62a21673d7a1bdccb849d5e06b73787e9d0b497ff435a1
|
| 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:eaa640453656a8011d107d1a50f43a1ce04fec3c1bfb6772fb85e9421b9a418d
|
| 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 sha256:675ec7cc45f55cee44a17f416147ee1d95912fc8344a9c65064804cf5a45b014
|
| 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 sha256:1a9bda5e7bf9f274121270e0c5ebfdb84cfb453c090fd10ad272483de82658f6
|
| 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,
|
|
@@ -19,13 +19,19 @@
|
|
| 19 |
"learning_rate": 0.0002,
|
| 20 |
"loss": 1.524,
|
| 21 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
}
|
| 23 |
],
|
| 24 |
"logging_steps": 25,
|
| 25 |
"max_steps": 728,
|
| 26 |
"num_train_epochs": 1,
|
| 27 |
"save_steps": 25,
|
| 28 |
-
"total_flos":
|
| 29 |
"trial_name": null,
|
| 30 |
"trial_params": null
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.10302197802197802,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 19 |
"learning_rate": 0.0002,
|
| 20 |
"loss": 1.524,
|
| 21 |
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 1.4671,
|
| 27 |
+
"step": 75
|
| 28 |
}
|
| 29 |
],
|
| 30 |
"logging_steps": 25,
|
| 31 |
"max_steps": 728,
|
| 32 |
"num_train_epochs": 1,
|
| 33 |
"save_steps": 25,
|
| 34 |
+
"total_flos": 817158545375232.0,
|
| 35 |
"trial_name": null,
|
| 36 |
"trial_params": null
|
| 37 |
}
|