Run 4. Outer Step 35. Inner Step 42.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549535,
-    5549538,
-    5549541,
-    5549543,
-    5549546
+    5549549,
+    5549551,
+    5549553,
+    5549555,
+    5549557,
+    5549560,
+    5549563
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f47f80b5140851d8e46a765b7d39b6060688755f7851bf3cf44d6d2082bf0b9
+oid sha256:4bc0c22339a39e04b5281777bdef7e049ab0739bf22cc45683d7fc1a342ffe6f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ea7da0bbdcc2ec5f2567a9397ec01e098749620cec5b4cc6c3e3cf9918b0a2
+oid sha256:81f787a66ca92fecc0011d516f3a955109716f4c4b287552e24619c75dd8d4c9
 size 4040701744