Outer Step 1. Inner Step 276. Batch Size 420

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5145848,
-    5145852,
-    5145857,
-    5145862,
-    5145866,
-    5145870,
-    5145875,
-    5145879,
-    5145884,
-    5145890
+    5145929,
+    5145934,
+    5145938,
+    5145943,
+    5145948,
+    5145952,
+    5145957,
+    5145962,
+    5145966,
+    5145971
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 267,
+  "inner_step": 276,
   "inner_steps": 0,
   "last_allreduce_block": 5143202,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde8820c287724f8b51bb674c17fe2342239790a0159a91850e0b9c3cf50daf6
+oid sha256:dbd5bea84d329f1d73e2fb3465bf0dafae2759b5c874854adcd56b76846141a4
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce30c32572375377c8d1495a37a644553589beaeb660480ff5bef94040c2d6f
+oid sha256:330f0f6bf271a083c480f7cd9b4f89c9515eceed3db9fb126befece02e8c9333
 size 4040701744