Run 4. Outer Step 3. Inner Step 141.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484813,
-    5484815,
-    5484818,
-    5484821,
-    5484824
+    5484827,
+    5484829,
+    5484832,
+    5484834,
+    5484836,
+    5484838,
+    5484840,
+    5484842,
+    5484844
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 140,
+  "inner_step": 141,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42818c2fb17441da1a1dfab1ea51899ccc6a2762ed26db6b30831d8d40c61d8
+oid sha256:7c3d7c8142205002c11315552338a3136fdd02d70d05fd930cf163331a140e2e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af268b986765b66ec17205321f261664e8ef688ada76c190af9fa090557b3c6
+oid sha256:f4aef68d5ebbb6d3df6ef0d36ec4947be7c9cd5d642febad880b9f7707916511
 size 4040701744