Run 4. Outer Step 62. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611572,
-    5611576,
-    5611581,
-    5611587,
-    5611591
+    5611596,
+    5611601,
+    5611605,
+    5611610,
+    5611614
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9224ef0dc57a01ca90ad60a9b2947f2a6ea8343e75dca182b905caaa60dcd995
+oid sha256:7c930411985d7b82eb76e466c122eb5838b298c6c2841efa8f267ec097fe687c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3457ff5608ea7ec4b3c3c0510f0ea8c4e9534db0aaf522b29c0cebb2055626fe
+oid sha256:37f2b87fd1dffe4a316b148e13c0b2abd05c1fad513bcfe159e174852983a34d
 size 4040701744