Run 4. Outer Step 3. Inner Step 133.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484761,
-    5484763,
-    5484766,
-    5484770,
-    5484773
+    5484775,
+    5484777,
+    5484779,
+    5484782,
+    5484785,
+    5484787,
+    5484789,
+    5484791,
+    5484793,
+    5484795,
+    5484799
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 132,
+  "inner_step": 133,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180c583ec51bf2680105945cd0ffac2ab3941eda2d6c285dd6a7b7c7355a0feb
+oid sha256:fc82d498f3f3618f005ff7f1f0f2cba7482fb8809fac8ccef1490f40095b2ad5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a9e24311ff72759f09fbeac3a79cc3c759d4b0dc6467a6df68ff8801518c9f
+oid sha256:376400b756e2a8c47786b69413397970514e1700521222a0ad82a4614ea70667
 size 4040701744