Training in progress, step 9200, 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 sha256:140eb6fe8d664c9c3bbb1492610f0ce146a450fda83da79fd1c887a6c991a899
|
| 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 sha256:2ed5ca269cac15684453a3e39280c0d35b1b2b6177f574bdccfb08d6c600810d
|
| 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 sha256:0c9af87a85c4a5347884f62121805e2bb80f901b5ab2075fc92e50eed3ea2329
|
| 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 sha256:29b8b87e03ea592d013522fc7154f72fa28937c463e2b7607ff5dbb622b97e47
|
| 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": 18.
|
| 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,
|
|
@@ -788,6 +788,13 @@
|
|
| 788 |
"learning_rate": 3.933333333333333e-05,
|
| 789 |
"loss": 1.2269,
|
| 790 |
"step": 9100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 791 |
}
|
| 792 |
],
|
| 793 |
"logging_steps": 100,
|
|
@@ -807,7 +814,7 @@
|
|
| 807 |
"attributes": {}
|
| 808 |
}
|
| 809 |
},
|
| 810 |
-
"total_flos": 1.
|
| 811 |
"train_batch_size": 8,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.39712544914857,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 788 |
"learning_rate": 3.933333333333333e-05,
|
| 789 |
"loss": 1.2269,
|
| 790 |
"step": 9100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 18.39712544914857,
|
| 794 |
+
"grad_norm": 0.21506337821483612,
|
| 795 |
+
"learning_rate": 3.866666666666667e-05,
|
| 796 |
+
"loss": 1.2289,
|
| 797 |
+
"step": 9200
|
| 798 |
}
|
| 799 |
],
|
| 800 |
"logging_steps": 100,
|
|
|
|
| 814 |
"attributes": {}
|
| 815 |
}
|
| 816 |
},
|
| 817 |
+
"total_flos": 1.4358732525646381e+19,
|
| 818 |
"train_batch_size": 8,
|
| 819 |
"trial_name": null,
|
| 820 |
"trial_params": null
|