Run 4. Outer Step 35. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548321,
-    5548325,
-    5548330,
-    5548334,
-    5548338
+    5548343,
+    5548347,
+    5548351,
+    5548355,
+    5548359
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2ecaaff8acc31636c291aad5cda26446d0708f0256f4287f9fb0766a1a3639
+oid sha256:2cf0311d1558679290d57da0ef2cb92461381f7a20d5fb646b5a8aa81be51ad1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49c21fec1df3106b85079ff9a32c9ce3b5f7b9d015a4d7640de90c297414202
+oid sha256:47a47a50ad04316aaff4f0dcf937196f997eb47baad4920a9cca99b13dbe6e19
 size 4040701744