Run 4. Outer Step 57. Inner Step 35.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601917,
-    5601922,
-    5601926,
-    5601931,
-    5601935
+    5601940,
+    5601945,
+    5601949,
+    5601953,
+    5601957
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a427ca0f9b153c1354ed728da45383811644928b5b04ad1b45f80b3fda575e6
+oid sha256:7983084d9e3f0842b5c6760c30106ddfbfac6f5b81008fca03a76e73e6eee56e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15ba6e532b6a9959a21a40dba54a9465b14269af08330aca20e2e6272e13837
+oid sha256:957c33cd82ea5a9a7ab6d014c6895027942d47b5c17dfc187350850e612aa411
 size 4040701744