Run 4. Outer Step 57. Inner Step 32.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5585708,
-    5585711,
-    5585715,
-    5585720,
-    5585724
+    5585728,
+    5585732,
+    5585736,
+    5585739,
+    5585743,
+    5585747
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d423d4ac8b19146ba43f94e0e00f912095bacd22f43456401eed5f226293f979
+oid sha256:9a222652b45dfad7bd9d9a039843aca27dd608b0ea7a249b850a4e7fa2219220
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81ec8a69fc0fdddd01da5ce848757795e00a67cb7a5df5e2c3477990c4630b1
+oid sha256:95722cb223c346dc014b7f108162297c5acac0a37b676b51b5ae8d0feb5f8e6f
 size 4040701744