Run 4. Outer Step 53. Inner Step 30.

config.json

@@ -268,24 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588824,
-    5588827,
-    5588829,
-    5588831,
-    5588833,
-    5588835,
-    5588837,
-    5588839,
-    5588841,
-    5588843,
-    5588844
+    5588848,
+    5588850,
+    5588853,
+    5588855,
+    5588857,
+    5588858,
+    5588860,
+    5588862,
+    5588864,
+    5588867,
+    5588869
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80b1b21b0ad0d62c641c1bce0835194fa89393b045d20d3c90b65f78cf10efe
+oid sha256:6545ab6b36fd48e344c1ec40aaad5a1c4c2fdfb31410d60f45c3df8874f64f79
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e52412c7e6aaae2d41794c02e09d91f10c033825aa4589841327744ecef9c9
+oid sha256:0495afa02a84bee8b063af21014b98e348d10ad4e95e70a8812a15c0e7a82985
 size 4040701744