Run 4. Outer Step 62. Inner Step 35.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611604,
-    5611607,
-    5611611,
-    5611615,
-    5611619,
-    5611622
+    5611627,
+    5611631,
+    5611634,
+    5611638,
+    5611641,
+    5611645
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc268ded4475710ee59d7726d69c178633255756dc116f3fd00190ee90e432c
+oid sha256:1df482b2edfd71ba760ddf9788de92b84576b2a71687737595a84074cbfd1076
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598ea3f0e78cb087a1b76d7cd052805ef2f3606daa3a6828b4bcaa131062a9c2
+oid sha256:d567c7db6ce957011c02a9dbbb7c02aeff863fd13a9ae6231127e0c6336755a5
 size 4040701744