Run 4. Outer Step 62. Inner Step 4.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610666,
-    5610671,
-    5610675,
-    5610680,
-    5610685
+    5610690,
+    5610695,
+    5610700,
+    5610705,
+    5610709
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6225dcf5040510aec1ba18f0f12b5e3b353464f1de7f5d749f5d8586246433
+oid sha256:b76296797438b074ed80c63fe771a53f53eea05e6106cfcab7b6a04271beb349
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8ec1c6d835e2fe8d8499ebbf2433f4a59ce717c7626d50d1ead46888f08cf2
+oid sha256:7a7dc261a0ad957baf0c0c8c8e0f2d69c67984db656446ba3e7a363d261b3caa
 size 4040701744