Run 4. Outer Step 58. Inner Step 29.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586894,
-    5586899,
-    5586903,
-    5586907,
-    5586911
+    5586916,
+    5586920,
+    5586924,
+    5586928,
+    5586932
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5583387,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f97e96bb445a1f351df829cbd13f1e428922b559f90faabef87cd3fb917317
+oid sha256:0451f7cb79e961520914247739141103cbb26607f41ffeb20546043f3d035160
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d28eb0c3e2938ef168c744384ed83118965dc7e28995ed98a12738cdb327f1e
+oid sha256:90dcceb3c3e24ff85eaa59b05f034a7d2654545f5048656db5f74b64a1e7796f
 size 4040701744