Run 4. Outer Step 58. Inner Step 103.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5605541,
-    5605545,
-    5605547,
-    5605549,
-    5605552,
-    5605555,
-    5605557
+    5605560,
+    5605563,
+    5605566,
+    5605568,
+    5605569
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 102,
+  "inner_step": 103,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86d3a3813df021cb4f6b1ce74a4e6bda4f5e17038e1c8265fbd5ac2ea112361
+oid sha256:adbaaa45bbe72334d52511b24f9367da23ce1cda7a14831d8c5c0a42a22fa86f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434a2293f71abcce0621ea07f8b3e5d3e8716a2a193a2545d032b1146a445594
+oid sha256:75a6c3a8b1a9caf7ecae1685f0f1ffb98eac56c84f6ad7b6702f7e224f8946be
 size 4040701744