Outer Step 2. Inner Step 240. Batch Size 476

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5148513,
-    5148517,
-    5148521,
-    5148524,
-    5148528,
-    5148532,
-    5148536,
-    5148541,
-    5148544,
-    5148548
+    5148577,
+    5148581,
+    5148586,
+    5148589,
+    5148593,
+    5148597,
+    5148602,
+    5148606,
+    5148610,
+    5148614
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 231,
+  "inner_step": 240,
   "inner_steps": 0,
   "last_allreduce_block": 5146835,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c4fe21be17d952fd6fdfcfc9a36fd43bec53d7637337b45d4c1b18ac758f99
+oid sha256:1213de4d391e0bc516b554f91e33eed4f21fb29a664fe00449f88003fb7d299b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1993e8341cdf3d38060936e467de572ab109f235e6167f836d62ef710d40164a
+oid sha256:5811a9818bacfa4ae5f66aac2ca1f15f78527610d23d5411d3e79c5b9e397c3b
 size 4040701744