Run 4. Outer Step 52. Inner Step 36.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576138,
-    5576140,
-    5576143,
-    5576146,
-    5576147,
-    5576149,
-    5576150,
-    5576152
+    5576156,
+    5576158,
+    5576160,
+    5576161,
+    5576164
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28570965b05a4d3105a59e0d89b0fcce538ea01710a4eace95c53c894f47696a
+oid sha256:b9e51e52f1dc86f1d7f53f165009895fb20b16ecf296f6d430a2fc1b3478dbd1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532bfbc8a787ea8a4de79c9fa0951d870746866f6ea4d150dd3a1eaf7d06b5cb
+oid sha256:31835046bc1e1b09796b4943c8281a4fb3cd397684ba21c2cfa58230e673f358
 size 4040701744