Run 4. Outer Step 58. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586152,
-    5586156,
-    5586160,
-    5586164,
-    5586168
+    5586175,
+    5586181,
+    5586185,
+    5586189,
+    5586193
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382d3e48b2cd18d8a252b9ae05c85802dba45fabc031eb90c9010c7c6174d66f
+oid sha256:e08f72e52e77658c4c0577f155de189b3dd9fe743503924d63b659ef0248e5a2
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0200135922dc1acf69effa65d78a8c1fd9785e0be8f33cca2d379095cf58605
+oid sha256:842d1687cd3a51a24f8241a989f7c3b6441e451547a90085beb09f42bf04181d
 size 4040701744