Run 4. Outer Step 50. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572210,
-    5572215,
-    5572220,
-    5572225,
-    5572229
+    5572234,
+    5572239,
+    5572243,
+    5572248,
+    5572253
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5565072,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c20ec00aa8c9f9b81516fc7dd1b9ebe3547b702ec7f71db77838f8b966939df
+oid sha256:0f9c7bccc544d98fc49eff51b2cbf5bb44acddc7c33775f75c22b60ec49d7087
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7026a99d62e964570a11b4399b6e93be8c9561549592582b60f09c70689fd150
+oid sha256:c6af4b7d964fdb3182d1f5b7abf46d37a800a6d88466c3374776d25ffd978b61
 size 4040701744