Outer Step 1. Inner Step 138. Batch Size 188

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5144566,
-    5144573,
-    5144579,
-    5144583,
-    5144590,
-    5144596,
-    5144603,
-    5144611,
-    5144619,
-    5144624
+    5144661,
+    5144667,
+    5144673,
+    5144677,
+    5144683,
+    5144689,
+    5144694,
+    5144700,
+    5144706,
+    5144713
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 129,
+  "inner_step": 138,
   "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:ef914c12d050ad98402699087bb76a2de8a1faf950cc9194806c6d61518ba6c2
+oid sha256:6eb80e243f6aafdb03e20fcabaae86c6df181ffc576aa3878f39312b1eb41d96
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08617e2f2edddf9b3b41777ccbd2030bd9c50c1ddde3d2101577a08a360fdb33
+oid sha256:e8605a790e450bb86f3d64e078f767610bccd297afbb0e8488f31d6d79bb08bf
 size 4040701744