Run 4. Outer Step 25. Inner Step 42.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534635,
-    5534638,
-    5534640,
-    5534643,
-    5534646,
-    5534647,
-    5534649,
-    5534651,
-    5534652,
-    5534654,
-    5534657
+    5534660,
+    5534662,
+    5534666,
+    5534669,
+    5534671
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a077cf9d03d1f4637836adde06517c2245276f9b1fc0a8b48a22a23ae9a0ce2
+oid sha256:9798b0e1f64b4c7036a6982778991efb666705a7cca96e8f7f1c7f246e8f3941
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738bf66cead013b794dba8a4ad09a84885660dcf1bbac0648081326e4fb65666
+oid sha256:1a2ad29bc925278027fe4bb1de2e1030ae243f930935365368ebd3db84609368
 size 4040701744