Run 4. Outer Step 58. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586796,
-    5586800,
-    5586805,
-    5586809,
-    5586814
+    5586818,
+    5586822,
+    5586827,
+    5586831,
+    5586835
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5583387,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c64bf3ff3fa162e1aad11d1aec1c689db07388f7dd1590bec0aafccfccde26f
+oid sha256:1bf56f0157bda37827b8768428b96aff36c53f7ddaa7a37aba218e1529aa9832
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee263d5a6c5f6e76b9e4da54f11ca13d559e3b58a285ae154025e33047d5975
+oid sha256:19cc7b4994874b4a4a8a202ec96393df95958683a340a82fc1e49ac974ba3d84
 size 4040701744