Training in progress, step 11400, 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 sha256:1d8033aac43721e5faa657d96399c8fbe165ff32991793e1979ec7c86cc5e973
|
| 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 sha256:6f6a135df03ce780080e7a469152b37447383728aef1ea68e2ec7595d105b22a
|
| 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 sha256:84ad3e03ea8f1373be4094c36a51a592911fcd41841d1f34997a6e6d354f36eb
|
| 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 sha256:7c5035fa2112ddcadfc8569c177cf4a1b5a136573a2d394a844790425be035f3
|
| 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": 22.
|
| 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,
|
|
@@ -974,6 +974,13 @@
|
|
| 974 |
"learning_rate": 2.466666666666667e-05,
|
| 975 |
"loss": 1.2219,
|
| 976 |
"step": 11300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 977 |
}
|
| 978 |
],
|
| 979 |
"logging_steps": 100,
|
|
@@ -993,7 +1000,7 @@
|
|
| 993 |
"attributes": {}
|
| 994 |
}
|
| 995 |
},
|
| 996 |
-
"total_flos": 1.
|
| 997 |
"train_batch_size": 8,
|
| 998 |
"trial_name": null,
|
| 999 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 22.796438056553665,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 974 |
"learning_rate": 2.466666666666667e-05,
|
| 975 |
"loss": 1.2219,
|
| 976 |
"step": 11300
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 22.796438056553665,
|
| 980 |
+
"grad_norm": 0.23605312407016754,
|
| 981 |
+
"learning_rate": 2.4e-05,
|
| 982 |
+
"loss": 1.2221,
|
| 983 |
+
"step": 11400
|
| 984 |
}
|
| 985 |
],
|
| 986 |
"logging_steps": 100,
|
|
|
|
| 1000 |
"attributes": {}
|
| 1001 |
}
|
| 1002 |
},
|
| 1003 |
+
"total_flos": 1.7792345264304947e+19,
|
| 1004 |
"train_batch_size": 8,
|
| 1005 |
"trial_name": null,
|
| 1006 |
"trial_params": null
|