Run 4. Outer Step 66. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651464,
-    5651494
+    5651524,
+    5651554
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5651055,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbeceef8eff7c69dcb67025a57a88fc94602db1a5f70a3ac35b2d77fa03f68c3
+oid sha256:c5eb5cd696e66981a3b9bce5ea31f6a241fc51fd00169701b40811bb7efc7e2d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70a856d5b4ab7d3a3920084b4fae3728b456553483bb98f91430873c6a590c1
+oid sha256:2c55dd3321b74762929b01df868e046aaa7dd7c4e2ff152e680703c07191e0d2
 size 4040701744