Run 4. Outer Step 62. Inner Step 29.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611516,
-    5611519,
-    5611523,
-    5611527,
-    5611531
+    5611535,
+    5611539,
+    5611543,
+    5611547,
+    5611551
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4b263371828829621f0a18178980ce3915e139d44b0c285b6a417838bc24d6
+oid sha256:210450692fd594cd593520653ab197ea34db2026cdeedae483ad0831d93712c5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07a267c64acef589aae4c6b5203307dadb2ede5f254065f465ecbb5b529d50c
+oid sha256:e554ec625e1fa40da4f449e57e3058053dd892584fafe0212e31765d7c4ec992
 size 4040701744