Run 4. Outer Step 40. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555109,
-    5555113,
-    5555118,
-    5555122,
-    5555126
+    5555131,
+    5555135,
+    5555139,
+    5555143,
+    5555147
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7b25b5ca781909d989cdd9f028055f56810e2c4eeb1eddf9a0610966542f8
+oid sha256:f0ef2504da26b3ccffb2e8851697befa81be6eb53a153f640c81f6af3b04fc1e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:effa41553e7903c5066489d7ea81fe2f5cbb0b17e251c1b41e699f035aeede8c
+oid sha256:03fcd8e898d7ea1f9271acaa27b83a7903ce2a47f50eeeb8e516bc5aaec53a73
 size 4040701744