Run 4. Outer Step 43. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563054,
-    5563059,
-    5563063,
-    5563067,
-    5563072
+    5563077,
+    5563081,
+    5563085,
+    5563089,
+    5563093
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5560919,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d81634057870140778e035f5b21a67a7b585d4a597251f5faac7a07a7a6017
+oid sha256:8e30c692c00e3e33f5747c1b9d1cf1e5556719a840777306bb1ee7a20c5782d6
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ca6a8e1954da7994e108297c756a08835172f00f347c6a0e622bbe2f1ac453
+oid sha256:4474bf9ed07a8ae78464ec52de08a5c43de90047e23a4217af4c3355a8bb9464
 size 4040701744