Run 4. Outer Step 29. Inner Step 20.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539710,
-    5539712,
-    5539716,
-    5539719,
-    5539721
+    5539722,
+    5539724,
+    5539726,
+    5539728,
+    5539730,
+    5539733,
+    5539735,
+    5539737,
+    5539740,
+    5539742
   ],
   "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": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c3f89b1c2d953153ca8a8b532070c2387eb01264b43c9b678455413fb23307
+oid sha256:884e01dfc6bf7c4fe1e7eac8b680fa08007ea7dc3228ee34e4a73e37fd1d3f79
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b87b0755d59aaa758f1798c12a438e793aa1f78b95a935f382f70f00a29df6fb
+oid sha256:be0290538c45ec338bb50c3b79b32de3bc96a927bd063df662b75b5cd5fe5928
 size 4040701744