Run 4. Outer Step 15. Inner Step 83.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515483,
-    5515486,
-    5515490,
-    5515494,
-    5515498,
-    5515501,
-    5515505
+    5515509,
+    5515513,
+    5515517,
+    5515521,
+    5515524,
+    5515528
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6246375828b2e225518750ce6f19c0c4342cc7eec5805637cc3559711f388e3
+oid sha256:21acced9dec982af395a18a687c9f4193edffc1c419ce9b21c17a3c144e52347
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a3d5b7414201ac1fc8b4d4b6a2ae8905a45f7ef0faf94e10b871be86148e8e9
+oid sha256:9098d02fcfbe2530413e8b03110d86ec3197a5ac67fd007e70c49f9e976f772e
 size 4040701744