Run 4. Outer Step 48. Inner Step 43.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5570050,
-    5570054,
-    5570058,
-    5570062,
-    5570066,
-    5570070,
-    5570074
+    5570079,
+    5570083,
+    5570087,
+    5570092,
+    5570096,
+    5570100,
+    5570104
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92023e36c78f6c959a1651429c76965454671754ea7f59a547528b5fdf9773e8
+oid sha256:dcd23e2edcdb09c5085b3f97b8dfe7a2cf3d3df6818647d993c82b3b5e74e2bd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c16a9627ea0a6772bbde13fa5d4052a68b8aae439eed8ba50bc6ed40878a302
+oid sha256:bb1fbb3a194b313bc8dd89013342b97f7a2498f9558f67f5a66235936df6654b
 size 4040701744