Run 4. Outer Step 55. Inner Step 0.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580690,
-    5580695,
-    5580701,
-    5580706,
-    5580711
+    5580717,
+    5580721,
+    5580726,
+    5580731,
+    5580736,
+    5580741
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b39afd9d9bdc44e7df5dc0c5dee013c25583d6ea1241b5b6f6dc24d800f11a
+oid sha256:3bcf6d6d3324c81cfec8b673b9adfd0e1a17f8b9b907f825de1b1e6d9b5bfbf9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ec4d18b04052dea69ba28a4c5ed80378e45f38c342ae65fbd6d90f464ebc5f
+oid sha256:416b7e6236dd430e8e058d3e0a669d151bed0eb61ae2c5a500b26f50d13121d8
 size 4040701744