Run 4. Outer Step 52. Inner Step 39.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576175,
-    5576178,
-    5576181,
-    5576183,
-    5576186,
-    5576188
+    5576191,
+    5576194,
+    5576196,
+    5576198,
+    5576200
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a9871a0cb16d3761a1484fb5c7d746d214671854a029c4cb2ef4809b856693
+oid sha256:b9c1f36619fca127f35f2e24583ddb8647ce3d013d08dae6d71371075047fefb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8256a0d4e90465cb14683b1d3141bd9a75472c563120f07283ab7ae024b8926e
+oid sha256:4c4f48be92fbdf0c0ff83c19f38a5aafdb9564b182455f277268dfa6da532142
 size 4040701744