Run 4. Outer Step 52. Inner Step 20.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575615,
-    5575618,
-    5575621,
-    5575623,
-    5575626,
-    5575629,
-    5575632
+    5575633,
+    5575636,
+    5575639,
+    5575641,
+    5575643
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736db6e282bad80eb968f8b41a41c915931e1c90452c50b4a792bd95f19a4ea3
+oid sha256:1d2a6f6a9fa2f8c0e15981946365f85cf3d8c75d377dc5b807cad328bd995afe
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08343ceb8905482a441f8a39aaaf499639b6b3fb004a0ebc8ecce83509e19f91
+oid sha256:a6c3e0b89ab0f3255c5f70435dc22ae6ab86a020073bd406336879e6cf9dff80
 size 4040701744