Outer Step 1. Inner Step 267. Batch Size 84

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5145770,
-    5145774,
-    5145778,
-    5145782,
-    5145787,
-    5145791,
-    5145796,
-    5145800,
-    5145804,
-    5145808
+    5145848,
+    5145852,
+    5145857,
+    5145862,
+    5145866,
+    5145870,
+    5145875,
+    5145879,
+    5145884,
+    5145890
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 257,
+  "inner_step": 267,
   "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 sha256:062b63421d0a7238ce9c33975b5dc4f8aa48af218036506e78ea3e3c5754e04f
+oid sha256:cde8820c287724f8b51bb674c17fe2342239790a0159a91850e0b9c3cf50daf6
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5986cff993c4c898af0ed8e0e4b92bf5ec3f2d3db8537144b1f635cbe06d7452
+oid sha256:6ce30c32572375377c8d1495a37a644553589beaeb660480ff5bef94040c2d6f
 size 4040701744