Run 4. Outer Step 58. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586385,
-    5586389,
-    5586393,
-    5586399,
-    5586404
+    5586440,
+    5586451,
+    5586455,
+    5586459,
+    5586463
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18df99ee8c795b2a2e4b79b64bc3ac3521279d5db59b79e5352cd06e89cdf656
+oid sha256:8209a5944a1db29b36260b3aa810bfe3f043ed49a49644e83a60d3b4c41b3222
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ebaf2ba7b9c1baead56ba1793ea1f57517f117e77b9d9699db90fa4a4da885
+oid sha256:6a0301f852a52e95242a15b2da7ace07f085f4cf68a1c8c06e1370ca6d09337c
 size 4040701744