Run 2. Outer Step 2. Inner Step 125.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5330458,
-    5330462,
-    5330466,
-    5330470,
-    5330475
+    5330506,
+    5330510,
+    5330514,
+    5330519,
+    5330523
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 118,
+  "inner_step": 125,
   "inner_steps": 0,
   "last_allreduce_block": 5323221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27e325fbeb650ec7a92a18d43f9542fea7fd736db70c2d93e958622d5bb0ad5
+oid sha256:cede510da57c517f0b1a0c5e26fab23e1c05d836a7aeeb28033f9e76234218c3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a437958a47d427117213fa89e0f9bddc69c775f4f66a876bc7e2634dfd877abe
+oid sha256:d15b13e816da95bd9326c322cf5a5d3b70a0e715566bc9399462ccaeb66985aa
 size 4040701744