Outer Step 2. Inner Step 365. Batch Size 208

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5075810,
-    5075814,
-    5075823,
-    5075828,
-    5075832
+    5075847,
+    5075852,
+    5075855,
+    5075859,
+    5075862
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 360,
+  "inner_step": 365,
   "inner_steps": 0,
   "last_allreduce_block": 5063053,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7276e014f789478a0a7f230f96d10b76dfda9dd4d282b0ec3733a84e9f21bc6
+oid sha256:4b7c407d15cde705ade523c8dab24eab26e062f7da641d521d7f46516e7e16b3
 size 4040701744