Run 4. Outer Step 59. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5606999,
-    5607003,
-    5607008,
-    5607013,
-    5607017
+    5607022,
+    5607026,
+    5607031,
+    5607035,
+    5607040
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf42420ef4574ccab8c17139f87456c901144576ff2ff3e476dda1c42f4626cf
+oid sha256:6e8215890993fb4addc3900dde8d744dd20632da61843c172778ebead1ad7f9e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad00ba6ac38ab5bc2d761071c05da11c059985736543fab1cf6e0d3f9a534814
+oid sha256:d86195a63babd675156f4e18b9a741f28cc285f51e2ed1dd053281dc04c626bb
 size 4040701744