Training in progress, step 12400, 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:b16bef696d643f07b3b74c8e05298a90d16f8d6377bcfc3c92d7ed58d57dc478
|
| 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 sha256:64178181dbf154aa8840338b3a9cd793eb6f36c2a3240a459f9e58d74069bf32
|
| 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 sha256:89d08ed8d6cfd3ff9d1a96759159e76e5a09c5fb769c0396ef4ede20b9b1cacd
|
| 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 sha256:72c42a478dc2abce506266bee23681e656243611e73c868841a8a274a8f9cc7e
|
| 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,
|
|
@@ -1060,6 +1060,13 @@
|
|
| 1060 |
"learning_rate": 1.8e-05,
|
| 1061 |
"loss": 1.2227,
|
| 1062 |
"step": 12300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1063 |
}
|
| 1064 |
],
|
| 1065 |
"logging_steps": 100,
|
|
@@ -1079,7 +1086,7 @@
|
|
| 1079 |
"attributes": {}
|
| 1080 |
}
|
| 1081 |
},
|
| 1082 |
-
"total_flos": 1.
|
| 1083 |
"train_batch_size": 8,
|
| 1084 |
"trial_name": null,
|
| 1085 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 24.79612560537416,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 12400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1060 |
"learning_rate": 1.8e-05,
|
| 1061 |
"loss": 1.2227,
|
| 1062 |
"step": 12300
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 24.79612560537416,
|
| 1066 |
+
"grad_norm": 0.23044925928115845,
|
| 1067 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 1068 |
+
"loss": 1.2215,
|
| 1069 |
+
"step": 12400
|
| 1070 |
}
|
| 1071 |
],
|
| 1072 |
"logging_steps": 100,
|
|
|
|
| 1086 |
"attributes": {}
|
| 1087 |
}
|
| 1088 |
},
|
| 1089 |
+
"total_flos": 1.9353076662446064e+19,
|
| 1090 |
"train_batch_size": 8,
|
| 1091 |
"trial_name": null,
|
| 1092 |
"trial_params": null
|