Run 4. Outer Step 49. Inner Step 65.

config.json

@@ -268,27 +268,32 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571473,
-    5571475,
-    5571477,
-    5571478,
-    5571481,
-    5571483,
-    5571484,
-    5571486,
-    5571488,
-    5571489,
-    5571491,
-    5571492,
-    5571493,
-    5571494
+    5571496,
+    5571499,
+    5571500,
+    5571502,
+    5571504,
+    5571506,
+    5571508,
+    5571509,
+    5571511,
+    5571512,
+    5571513,
+    5571514,
+    5571515,
+    5571517,
+    5571518,
+    5571520,
+    5571520,
+    5571522,
+    5571523
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5566279,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d667291f54bab9c5abaa7fca6e7f225f7500b7bdf4f604fe3b0267359556ed1e
+oid sha256:d92191c19e4f1c03bd3bf67a84b4c0efb8b024f3684d26fba2c9d7c4bfb4e12d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f28b485c3608e70cf96a94f098e91babd800b659891d6caf2c5c309d09977c6
+oid sha256:70c561ce99e928e9805c9395094af5aa00c667d543f3868c1bfc6766a0fbef89
 size 4040701744