Run 4. Outer Step 58. Inner Step 4.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604629,
-    5604633,
-    5604637,
-    5604642,
-    5604646
+    5604651,
+    5604655,
+    5604660,
+    5604665,
+    5604668
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22768f1386768eba7c4c0fb3d8562fcbf24bcea7148546fa1f60fe96e36cb4cd
+oid sha256:e7ba60c2a08df214f760e5d9de17687e64ee04dc5ed485906cfb986a47d439f4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbc6e5eb85be82f6c8b08965712cfb16dc0da997037220e3a598ab7eb6d0021
+oid sha256:ce5015c1de3350375aa958ce80d688028ec4d2895f24bde9bdff2aebcc52efad
 size 4040701744