Run 4. Outer Step 58. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603225,
-    5603232,
-    5603239,
-    5603246,
-    5603253
+    5603261,
+    5603268,
+    5603275,
+    5603281,
+    5603288
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dacadb457878a1976f27c52869b6d2947b5e89f33752647896f8d5b8dc4edb8
+oid sha256:c2e3930db9f4f94ff4d6bb6e067fe2b5d00f4a4ec2c2a90f95c725fdc2ebc02d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa8f9cd8c560bd4ded292e4b829a44fbdf214aedb46b717f3e12507d1bdb22a
+oid sha256:9fc82252e187f3b24618c9c6aa3521265ddec832fc144ca5e1ac5544c18b334f
 size 4040701744