Run 4. Outer Step 58. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586612,
-    5586616,
-    5586620,
-    5586624,
-    5586629
+    5586638,
+    5586642,
+    5586646,
+    5586650,
+    5586654
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f661105f5d78242397ab28ee8abd86f6ba9dedae97517fcf07f67ceba59911
+oid sha256:2fdc6b970da39cca9b8bce7fb8a5667571702d487ca001ab341d9201576e65dd
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7935bbeca3cdb9078bd336832c8afcd7b0bd7b22501ba2b76035c7b6c7a0533
+oid sha256:38e0c02b2b6bd474e79de34cde2825cd2909f43a73bd6e506225b9f7d49251e1
 size 4040701744