Run 4. Outer Step 58. Inner Step 3.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5587594,
-    5587597,
-    5587600,
-    5587600,
-    5587605,
-    5587608
+    5587611,
+    5587614,
+    5587617,
+    5587620,
+    5587623,
+    5587625
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "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 sha256:3a212ced91e33761bf657a1e544dd9650ad355f59cd8929d29bbe86bb9a8ae5e
+oid sha256:0b8afd2a83e5263225d08927ba7566d51425530bd969052723a2337b4ca11dbe
 size 8081782439

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ad277e83a5a65e55c19bc379d342307880570fe396adac2d50bbe0dc2120f1
+oid sha256:e196a113d9df02a78666ef36be0bc07043696327734409d63752df3e8bc4fbb9
 size 4040701744