Run 4. Outer Step 50. Inner Step 68.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5573405,
-    5573409,
-    5573412,
-    5573416,
-    5573420,
-    5573424,
-    5573428
+    5573433,
+    5573437,
+    5573441,
+    5573445,
+    5573449,
+    5573453,
+    5573457
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25de9b8556c76fa92a9b3c6b0cc02fbeb32681061a6d0e503b68a6d1898da19
+oid sha256:76e1e0e589447084e7f988038d87c155ec246f28f878b57669df6d61b7b5725c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3afe56405554e35a9abedf7874b9f612ac92d6c7d23afd091571b524e70157
+oid sha256:d0261a2a1db05c24c1ce14f88e8a71d196bb0ef3b563c15d72709f43610269a2
 size 4040701744