Run 4. Outer Step 65. Inner Step 48.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5649293,
-    5649323
+    5649356,
+    5649385
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 45,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5639485,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b266bf7e8bee247464a3ca2265eaa7b675d58a1de79efbb8fe5779bf6693df
+oid sha256:adf3002034d0d6b8f55e6cb3fc795b726cbfa9d2bb20d38a795469a3049e4eb1
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f13a2bf04b2ce1164058dae754c11165e4804fc3cbdc306b297525ec68cbaa
+oid sha256:b413f60c823ef495c24e78f0042a96c55c8313b9100a713274199a638f46188a
 size 4040701744