Run 4. Outer Step 52. Inner Step 35.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576055,
-    5576058,
-    5576060,
-    5576063,
-    5576066,
-    5576068,
-    5576070
+    5576073,
+    5576076,
+    5576078,
+    5576080,
+    5576083,
+    5576086
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "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 sha256:28c2e378d62fb0aafb6e80fec8f60f6151bb0977b49d30e1635bc2c731a34f94
+oid sha256:ad26cae1ffb11d892a3935b8c161624a8532157513ebef684d73c7d04c15c2fb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20613c07ee1cd5f44187e9f5c9fdaceb4ccd6a085b6a708c07a304cc02bb558
+oid sha256:a1667e3b7372ce7f442c6b3c289aa4a16adcbf0bd9002850b001585c9c39cc36
 size 4040701744