Run 4. Outer Step 3. Inner Step 134.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484801,
-    5484803,
-    5484806,
-    5484808,
-    5484810,
-    5484813,
-    5484815,
-    5484818,
-    5484820,
-    5484823
+    5484826,
+    5484828,
+    5484831,
+    5484834,
+    5484835
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 133,
+  "inner_step": 134,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc82d498f3f3618f005ff7f1f0f2cba7482fb8809fac8ccef1490f40095b2ad5
+oid sha256:57528b21b21556e88940924b904c5a98ee41c70d23264cd0b5038736512834e9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376400b756e2a8c47786b69413397970514e1700521222a0ad82a4614ea70667
+oid sha256:8da4596e20f5155c643381db27b44d9c0ec2557e46b38e00a144f4a62873100f
 size 4040701744