Run 4. Outer Step 55. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5593145,
-    5593149,
-    5593154,
-    5593158,
-    5593162
+    5593168,
+    5593172,
+    5593176,
+    5593180,
+    5593184
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5591842,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95696036425b42d79db274b9b35260fdd002aa47375457bd59016634d2e28b6a
+oid sha256:8c52ade3637983b919c6c1174c7b7ac09c9ff1d4c868b930be1dfbbbb4fd7874
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97672702951f39d7ecd90de7ed61819a58484ce74254b7d88f15796091e3c825
+oid sha256:0831593b352be15794682c56acf7ee569275a6f6af293a3b50ef2b2f705df8f5
 size 4040701744