Run 4. Outer Step 52. Inner Step 31.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575995,
-    5575998,
-    5576001,
-    5576005,
-    5576008
+    5576011,
+    5576013,
+    5576016,
+    5576019,
+    5576021,
+    5576024,
+    5576028
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "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 sha256:2dc516e91b6e61091b9793bdd59261de3cb9c7d61cfe737dae2e7da38db1e1b3
+oid sha256:247a793d78e860335c1b46cc73314e4304eb3eeb016293a59f4bfb38595d747a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7dd979ac205adb379940dbf7debe074719c93d8cf817f44a47a69e8c8ffb463
+oid sha256:467efebee360a489010f99e01fde0eaa1b7caa5eb72e6482fab444e19a05bfb9
 size 4040701744