Run 4. Outer Step 50. Inner Step 165.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5626676,
-    5626703
+    5626732,
+    5626759
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 163,
+  "inner_step": 165,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa861da33df89200b7e98bacff3f9776e479ae8e9de869ffc4d8dac3151a3288
+oid sha256:e8476501417df658d6153431bfb959195463ea4936f94cb83a0e0d2fcbe18ade
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b296c3ea37a5c46d6b758e4f8f1664a722903a74a80a461ecf9f23632d2fa25
+oid sha256:0b631996707d9dd22e2a5e8d23726a6aa7adf0ae5d0a5e3cb02ec55498c872c4
 size 4040701744