Training in progress, step 12200, 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 sha256:3c951252bb0ceff63af1472253f0f51296efbc10a2a34cafc9ce737d5604b25e
|
| 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 sha256:5bec49532d0c9469d6aa8180783edb97c47ab00b3efc388784187682576fe73c
|
| 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 sha256:782e6fccb7e358f57c281fa2552111132f0efcd2a1f29720ae037c0f86ade2ca
|
| 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 sha256:670890a7ca0ec632da074caaf14a94a802df653090a9d0d3499e4281fd5e1a9f
|
| 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": 24.
|
| 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,
|
|
@@ -1046,6 +1046,13 @@
|
|
| 1046 |
"learning_rate": 1.9333333333333333e-05,
|
| 1047 |
"loss": 1.22,
|
| 1048 |
"step": 12100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1049 |
}
|
| 1050 |
],
|
| 1051 |
"logging_steps": 100,
|
|
@@ -1065,7 +1072,7 @@
|
|
| 1065 |
"attributes": {}
|
| 1066 |
}
|
| 1067 |
},
|
| 1068 |
-
"total_flos": 1.
|
| 1069 |
"train_batch_size": 8,
|
| 1070 |
"trial_name": null,
|
| 1071 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 24.39618809561006,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 12200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1046 |
"learning_rate": 1.9333333333333333e-05,
|
| 1047 |
"loss": 1.22,
|
| 1048 |
"step": 12100
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 24.39618809561006,
|
| 1052 |
+
"grad_norm": 0.23374997079372406,
|
| 1053 |
+
"learning_rate": 1.866666666666667e-05,
|
| 1054 |
+
"loss": 1.2256,
|
| 1055 |
+
"step": 12200
|
| 1056 |
}
|
| 1057 |
],
|
| 1058 |
"logging_steps": 100,
|
|
|
|
| 1072 |
"attributes": {}
|
| 1073 |
}
|
| 1074 |
},
|
| 1075 |
+
"total_flos": 1.904092672006973e+19,
|
| 1076 |
"train_batch_size": 8,
|
| 1077 |
"trial_name": null,
|
| 1078 |
"trial_params": null
|