Run 4. Outer Step 31. Inner Step 28.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542011,
-    5542013,
-    5542015,
-    5542017,
-    5542020,
-    5542022,
-    5542025,
-    5542027
+    5542029,
+    5542031,
+    5542034,
+    5542037,
+    5542039
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a4a492cc69c54059ada861485bd16a0c5044786db88c886f643872395f3e4f
+oid sha256:0bec140565e64feca799d590cb9c5a1e1b7e81fb8398e1968706333552aa0b6f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4028550f1775b9bebc17e652ba9eac23864de2f8461e541193e5470d0531297
+oid sha256:f56ee8ab940ef091f6b1b1ff89653a091c9d0ccddcf4152be609f40f835582f7
 size 4040701744