Run 4. Outer Step 62. Inner Step 34.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5644112,
-    5644116,
-    5644120,
-    5644124,
-    5644128
+    5644133,
+    5644137,
+    5644141,
+    5644145,
+    5644150
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb98c3ae893a0691a50b318ec745dd187a78889dfd7a6c98a5e55caf637e50c
+oid sha256:22af522cb211a49762a63a35a7f37cadbed63cd7a6056fb71dc88f5c186a6f6f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15aba8c25122fbb3b0a97cd6a1d48f9b9727e9ec05955842c1da44493ba9dc73
+oid sha256:f3b5ee1e04854f8d64e763598f365d330003bec55f4f6e8ca9bd543464b4b046
 size 4040701744