Run 4. Outer Step 36. Inner Step 40.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550728,
-    5550731,
-    5550734,
-    5550736,
-    5550738,
-    5550741,
-    5550743
+    5550745,
+    5550748,
+    5550749,
+    5550751,
+    5550753
   ],
   "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": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c23c047b4087fc9243e37228535208f6137e70de28cc28389b7f8090c530892
+oid sha256:bb744d05b824b928de637d6f8c08311a0f8c8b5a0c661fb44ab69035b287ef0d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389b813d20175f0f88b02d486777a2e1be3b018ad15e3ae4c5243f59e6ae9750
+oid sha256:d489480be60d88b06225a45fe0ad92ffe9e3c37bc5d63c6162205c90aafed4b5
 size 4040701744