Run 4. Outer Step 57. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601613,
-    5601617,
-    5601622,
-    5601627,
-    5601633
+    5601638,
+    5601644,
+    5601649,
+    5601654,
+    5601660
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6cc7bd9fd9557021676ec56201ad91c44eac7d4ae39f96e81ff8fe37afe8f4
+oid sha256:cfddec09962146f7ed472ecc632ef0614722fda862419cfcda08cab4bd6914a9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6e927e29168e557869fc8b62ff7aec2f57bc70de6db8de518d445372ead20c
+oid sha256:2ad95f7af5ef625719ecd255a675260a6767fb09f38d0b20ac13d202939ad826
 size 4040701744