Run 4. Outer Step 57. Inner Step 38.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602066,
-    5602070,
-    5602072,
-    5602074,
-    5602075,
-    5602077,
-    5602079,
-    5602081
+    5602084,
+    5602087,
+    5602089,
+    5602092,
+    5602095
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b2fc659b468e5f8810a1c0b962ab87dfb328bd9ef92b34255139896d9d62fd
+oid sha256:e48ef2746d5bd5818e1a74b9df820d9035e17d80bd91edb673f068068f174a81
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9853812d91222dafd95ed9aa1f247a2aeb9604578f97535062dd252bd4296edb
+oid sha256:436f583475d68d54ce45ca055ba70b151b6f1bf74b9c2446017cebb56fc0d000
 size 4040701744