Run 4. Outer Step 10. Inner Step 88.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506124,
-    5506128,
-    5506131,
-    5506135,
-    5506139,
-    5506143
+    5506147,
+    5506150,
+    5506154,
+    5506157,
+    5506161,
+    5506165
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 87,
+  "inner_step": 88,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccdfbac9ce91dec765c7e2f416dd3e2f4fc428947680dfeb105b02421b7abc0d
+oid sha256:49259d3854b6e113d0120b135fc48afa333d4ad779e24b4dad786aa87bcb3cb2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13bc76913087a0f29e30469b136401d0370332e09c9d3b69fea7fe2922673ea9
+oid sha256:857d60231575e605571e5683bb349ef9b85cc3dd78ef6669356908604970e62b
 size 4040701744