Run 4. Outer Step 47. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5568416,
-    5568420,
-    5568424,
-    5568428,
-    5568432
+    5568437,
+    5568441,
+    5568445,
+    5568449,
+    5568453
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5567600,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974a71fae0880efcba460d59196645b77757287fb6edf5909c374302ce70c8c7
+oid sha256:8c7e85a18c78702a3c60f60de7109fbcca746e49b8e09defe729cbb091bfc5fa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e205c6d18d1ca10cfb08b618fd51de34466f78aab50859809e2a6c682e323d
+oid sha256:64e50a7950982dbbe62f931366e0d2edfad29de1e21cb1db4226fa51aeadb53b
 size 4040701744