Training in progress, step 10300, 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:c49eb58c1575317e47de352f8cffc3efadb099c22cd05f568eedffb7494d62c4
|
| 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 sha256:710ff57751d5c2c8f79e0d61ec896e43dbbe40dd5cc532e6f6a35ec2b257d534
|
| 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:fbc129d2d4d92a03a12b8745b6983f52cddef674fd684e2426d697fd5061143c
|
| 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:a5075bb2ff7d5606a50c10ad8e780b4590bed3ade26bcf04be4fa6958d53dddd
|
| 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": 20.
|
| 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,
|
|
@@ -881,6 +881,13 @@
|
|
| 881 |
"learning_rate": 3.2000000000000005e-05,
|
| 882 |
"loss": 1.2271,
|
| 883 |
"step": 10200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 884 |
}
|
| 885 |
],
|
| 886 |
"logging_steps": 100,
|
|
@@ -900,7 +907,7 @@
|
|
| 900 |
"attributes": {}
|
| 901 |
}
|
| 902 |
},
|
| 903 |
-
"total_flos": 1.
|
| 904 |
"train_batch_size": 8,
|
| 905 |
"trial_name": null,
|
| 906 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.59678175285112,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 881 |
"learning_rate": 3.2000000000000005e-05,
|
| 882 |
"loss": 1.2271,
|
| 883 |
"step": 10200
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 20.59678175285112,
|
| 887 |
+
"grad_norm": 0.23765605688095093,
|
| 888 |
+
"learning_rate": 3.1333333333333334e-05,
|
| 889 |
+
"loss": 1.2212,
|
| 890 |
+
"step": 10300
|
| 891 |
}
|
| 892 |
],
|
| 893 |
"logging_steps": 100,
|
|
|
|
| 907 |
"attributes": {}
|
| 908 |
}
|
| 909 |
},
|
| 910 |
+
"total_flos": 1.6075538894975664e+19,
|
| 911 |
"train_batch_size": 8,
|
| 912 |
"trial_name": null,
|
| 913 |
"trial_params": null
|