Run 4. Outer Step 42. Inner Step 35.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560725,
-    5560730,
-    5560734,
-    5560738,
-    5560742
+    5560747,
+    5560754,
+    5560758,
+    5560762,
+    5560769
   ],
   "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": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3154b3b9265e92a3bb36bc093c7fa697640ae2ce511c236d8e0e85144c34426d
+oid sha256:8309a3906397b39a7b76ba9f2653a0e4e1dd80825be68364629cc6a7007adb1f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d971b2653066a83466d50f957a12cdf17f83ed6023b0ee9cad04ad98e9dc0346
+oid sha256:2a690cba5d2748bb85be685f4dcff4ef5ab34b83768ae31833a7dbfd1388842f
 size 4040701744