Run 4. Outer Step 78. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5666033,
-    5666047,
-    5666062,
-    5666076,
-    5666080
+    5666088,
+    5666093,
+    5666096,
+    5666101,
+    5666105
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5665748,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c5c79f9df28df32e843442005bb454f900a6fe92c43a6a41cd51b7cdb0ccfb
+oid sha256:4c1ab41219df16174c0656688c5f3ccbb0440293d454fd3d3f2d2ea5e723b00c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e019741a90acf9332ac7259f44c1b34c7996fba50169901cbcbf00bf6f7126a
+oid sha256:edff1b67d9b4ce4f5396d334efc5dcce55c99d17f7a571b60ef7c4e3f1dfc84d
 size 4040701744