Training in progress, step 10700, 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 sha256:8cebcb7e1a9287ef1e080dd176b9ea27828f7dcd6cd5a20a388280eda599fa4f
|
| 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 sha256:82cc8a015efcd1420728977e71a79d6c2f2b8ce61e2d7326a4ba38932f76586e
|
| 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 sha256:49b3cabf5cef297feac3f098e48e81f82c6a617482b5093d104f798f397e765f
|
| 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 sha256:947bfc49c7f9b10a26d2ed20ec6f50d55fe47b3bb165118aa1edd5a7ea75d537
|
| 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": 21.
|
| 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,
|
|
@@ -917,6 +917,13 @@
|
|
| 917 |
"learning_rate": 2.9333333333333336e-05,
|
| 918 |
"loss": 1.2215,
|
| 919 |
"step": 10600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 920 |
}
|
| 921 |
],
|
| 922 |
"logging_steps": 100,
|
|
@@ -936,7 +943,7 @@
|
|
| 936 |
"attributes": {}
|
| 937 |
}
|
| 938 |
},
|
| 939 |
-
"total_flos": 1.
|
| 940 |
"train_batch_size": 8,
|
| 941 |
"trial_name": null,
|
| 942 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 21.396656772379316,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 917 |
"learning_rate": 2.9333333333333336e-05,
|
| 918 |
"loss": 1.2215,
|
| 919 |
"step": 10600
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 21.396656772379316,
|
| 923 |
+
"grad_norm": 0.2331283688545227,
|
| 924 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 925 |
+
"loss": 1.2249,
|
| 926 |
+
"step": 10700
|
| 927 |
}
|
| 928 |
],
|
| 929 |
"logging_steps": 100,
|
|
|
|
| 943 |
"attributes": {}
|
| 944 |
}
|
| 945 |
},
|
| 946 |
+
"total_flos": 1.6699829622858056e+19,
|
| 947 |
"train_batch_size": 8,
|
| 948 |
"trial_name": null,
|
| 949 |
"trial_params": null
|