Run 4. Outer Step 52. Inner Step 40.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576210,
-    5576212,
-    5576215,
-    5576217,
-    5576219,
-    5576222
+    5576226,
+    5576229,
+    5576232,
+    5576234,
+    5576236
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84bbc35ba5078485b4ff73552171fb2075f8146b6046e73ad232edf7eb6bfc4
+oid sha256:c93d53146904ec4975413cb946fa81b67821b0db45bb6dfe770e216b8f340fda
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5473e8f1919b47e5c95b99ac9227840d369391885e429b0e35b530c8be83c361
+oid sha256:3953a71e916f0d3881d7c5357f01324ab8a436a99adcfb5634b8ae4c66d554e7
 size 4040701744