Run 4. Outer Step 40. Inner Step 50.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556567,
-    5556568,
-    5556571,
-    5556574,
-    5556576
+    5556578,
+    5556581,
+    5556583,
+    5556586,
+    5556588,
+    5556590,
+    5556593,
+    5556595
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 49,
+  "inner_step": 50,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f6beb855c3e98ce86c7ec61bdaff917a688deffb0f142c2b412dfa46cef763
+oid sha256:7022d16ec6d3d92056984d4c2dc93e9c113da91d992e34c737725704a41e295b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e2cc095f59597733311b906de0a8d754fc5d14afec02ce8bb142e2c5d30ab5
+oid sha256:6f009b3b786350011210e6d86a3954d05007d593dad6b48d6ef1791bd41bda96
 size 4040701744