Run 4. Outer Step 64. Inner Step 235.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617666,
-    5617670,
-    5617675,
-    5617680,
-    5617684
+    5617689,
+    5617693,
+    5617698,
+    5617703,
+    5617707
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 234,
+  "inner_step": 235,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b930e6e62eb009c8b2f23b02509b0c32bef0b79bf838f04458cbc3d676fd68
+oid sha256:440e0e9e754842c6c58ae12aeec4710aeb01e1046e6e209f8f4a54b2b14b4184
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f391fd7a5fe94025009f335c7d93b2cd81475946d5db5da9f1ffbd371fcc99f
+oid sha256:56f0904cbeeab915d5454a0518e894a64cd99b73425fca379d91e70444569cd6
 size 4040701744