Run 4. Outer Step 61. Inner Step 66.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642858,
-    5642863,
-    5642867,
-    5642871,
-    5642875
+    5642880,
+    5642883,
+    5642887,
+    5642892,
+    5642895
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c112ed5f10ae62de38575a1f4e63daf739c0ec49245eff36729ebafc19d91122
+oid sha256:0ddee9616b8d3137b454754d3bed54c9fa1e9ba8fb80ed79048715fa949f3686
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8e58fc4452cd0d0dacbfe7736b9256ed8754e7ec0a1a3e1d220b2d309e2d67
+oid sha256:7b0ec2030355f977caac9590de240287baf5a310312d4ec8f1536eb2f0f08ac3
 size 4040701744