Run 4. Outer Step 57. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601402,
-    5601409,
-    5601416,
-    5601423,
-    5601430
+    5601439,
+    5601447,
+    5601454,
+    5601461,
+    5601468
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "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:fd6cbe8f10450917bb70ea7c870b10c3bdaa9127d01affa44dc9e99a051ac260
+oid sha256:b3232b1903d086acb553cea70a9529af77096e68c3f5c68458bdba60cba9f47f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2353655db60603ada6a0d79ce10b62192483ad6646e2108360a52236903a613
+oid sha256:eb89d2948829b2df28124448c99f42541c0039bac44128b15d3c4511010d1308
 size 4040701744