Outer Step 0. Inner Step 80. Batch Size 248

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5140161,
-    5140165,
-    5140170,
-    5140174,
-    5140178,
-    5140182,
-    5140186,
-    5140189,
-    5140193,
-    5140196
+    5140225,
+    5140229,
+    5140233,
+    5140237,
+    5140241,
+    5140245,
+    5140248,
+    5140252,
+    5140280,
+    5140296
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 71,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7eb76d32ef7c8e50f0f7450a5fc44ffda2117036536ef0227bc9ff469dd4625
+oid sha256:42ce6f6f6d88ef5f5eca6f160b4857494b58b06fce4ba3402d9f5b9e625f775b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3bab87cd4e07e2ca86bf72c0fd995754bc87f3105b122ad9cd079e34d644fa
+oid sha256:505a09a1aa96ce0180585e528d05e1dff8851c29ec4e6225589dc5b67fa1736b
 size 4040701744