Run 3. Outer Step 6. Inner Step 287.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389750,
-    5389754,
-    5389757,
-    5389761,
-    5389765
+    5389797,
+    5389801,
+    5389805,
+    5389808,
+    5389811
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 284,
+  "inner_step": 287,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8e87bbc18fe1ea136b108755776ca5d5002d27a95995bad6e704b4c49b8774
+oid sha256:521f56effeee0d4f09b4a6e71075764e6d4d16645ced6c8b0694b9332ccdd053
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1277270b37d1396582b40e80534ee3c3137d092c3489190251418529525fa6
+oid sha256:7436f00482c2148be8a294262d6bea78fa12e726111d1768d9f098043169d321
 size 4040701744