Run 4. Outer Step 54. Inner Step 95.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5598203,
-    5598206,
-    5598208,
-    5598209,
-    5598211
+    5598213,
+    5598215,
+    5598217,
+    5598219,
+    5598221
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 94,
+  "inner_step": 95,
   "inner_steps": 0,
   "last_allreduce_block": 5590498,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5927b4d75978d3fae2940f1c6b5facb348b1ef9a9492e6290e3e36307f3dbd81
+oid sha256:7be5eb83fbe985c9e03cd2e58ea36c3a5c8b2fba12c94c615db0209dff226592
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edc487cb3af40b4d57e9caccd05d302b263a0bc1327af7f079f52fbc2c6043a
+oid sha256:8e116393d572fb78ef24732a50d31e95a7290ebb281cbb1c135a0bcc5b88fecc
 size 4040701744