Run 4. Outer Step 50. Inner Step 83.

config.json

@@ -268,18 +268,14 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5622527,
-    5622531,
-    5622537,
-    5622540,
-    5622545
+    5622570
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "inner_steps": 0,
   "last_allreduce_block": 5563454,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e73402907a6d38e0e486559842f7448d4507c9598eaf3eceada5dde9efdefe4
+oid sha256:53a31d219974cc4ccb0dc4893bb50486620d370ab3d3baea59a894521e7e658a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335f02cc50bce1999005568f8f26b3f62a26fa4ec6a57530a351ee721caacc7c
+oid sha256:30911d53c7d8ab8502f8c05da77c322d40cd145956681b47e174bf15127e1113
 size 4040701744