Run 4. Outer Step 64. Inner Step 233.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617598,
-    5617602,
-    5617606,
-    5617610,
-    5617614
+    5617619,
+    5617624,
+    5617628,
+    5617633,
+    5617637
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 232,
+  "inner_step": 233,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c7ea9dde29845b5a19144fe0bfb8f717c34eb45c022b4edc4aa319141e9cd6
+oid sha256:d0fb0d6873ceccc84b10232171f925041d67350a3ff929e0a04c6f6cffb9d807
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3252f09adaf83a55658395673ed43da11e3d209dd8384f526a07a101c9b65c84
+oid sha256:7a1bc8c2400bfdb104f0e25d6415f616198b3209892caac7a2328286bf539c93
 size 4040701744