Run 4. Outer Step 42. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5559956,
-    5559960,
-    5559965,
-    5559969,
-    5559973,
-    5559977
+    5559983,
+    5559987,
+    5559992,
+    5559996,
+    5560000,
+    5560005
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b8d0889a61bc9e73d7dfaf5c4197098aec0077dd74c0570238a7dec99d351b
+oid sha256:cecf23ba8287b48e3b6696a682b8d0f1d383b5059a9eac45b70a79826c407177
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2b244fcf818e7961f5e82bb6685bab2f0c79d9b2d784a6cde66ccb563e6818
+oid sha256:506565985a99681c619a65d11befd918e769a39797edfcfc2dcca358e8811dbc
 size 4040701744