Run 4. Outer Step 54. Inner Step 132.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597811,
-    5597815,
-    5597820,
-    5597824,
-    5597828
+    5597833,
+    5597837,
+    5597842,
+    5597846,
+    5597850
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 131,
+  "inner_step": 132,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2365b778ce5ecdc37a9ee55355461d00d4cb925a9948890d2306e12d5e6336a
+oid sha256:a6acc00dad1d030a23003f9499c3ae8b3395089e23905d9b65390d6ce84c263d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef096170a1e8e96ff979e3869cfa4b903132fffb29a873cda7c13a34805536d5
+oid sha256:e397b844e4ed473523aa3ef56f3b3fc338920dfc4a08a526c1b4f2ebfffefba2
 size 4040701744