Training in progress, step 9900, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6deea05c166b89fc877ff2e3f92f12973dd0d4ad7605db80ff585b7d98a8fe47
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cce451040d8df50777438a10389a653ccc5f6777ba24e9c371e90b67b46f8d1
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56eab8a6ae855f6d831826ceedcd72e607560d7887ae0f290c0ac887815f7455
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7727bca6739367d2a9130b4e43b9681ded2d27ee732ac63a61df75ffcc18c7fd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 19.
|
| 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,
|
|
@@ -845,6 +845,13 @@
|
|
| 845 |
"learning_rate": 3.466666666666667e-05,
|
| 846 |
"loss": 1.2268,
|
| 847 |
"step": 9800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 848 |
}
|
| 849 |
],
|
| 850 |
"logging_steps": 100,
|
|
@@ -864,7 +871,7 @@
|
|
| 864 |
"attributes": {}
|
| 865 |
}
|
| 866 |
},
|
| 867 |
-
"total_flos": 1.
|
| 868 |
"train_batch_size": 8,
|
| 869 |
"trial_name": null,
|
| 870 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.796906733322917,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 845 |
"learning_rate": 3.466666666666667e-05,
|
| 846 |
"loss": 1.2268,
|
| 847 |
"step": 9800
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 19.796906733322917,
|
| 851 |
+
"grad_norm": 0.2173725664615631,
|
| 852 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 853 |
+
"loss": 1.2232,
|
| 854 |
+
"step": 9900
|
| 855 |
}
|
| 856 |
],
|
| 857 |
"logging_steps": 100,
|
|
|
|
| 871 |
"attributes": {}
|
| 872 |
}
|
| 873 |
},
|
| 874 |
+
"total_flos": 1.5451248167093273e+19,
|
| 875 |
"train_batch_size": 8,
|
| 876 |
"trial_name": null,
|
| 877 |
"trial_params": null
|