Run 4. Outer Step 54. Inner Step 93.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580375,
-    5580378,
-    5580380,
-    5580383,
-    5580385,
-    5580388,
-    5580390
+    5580392,
+    5580395,
+    5580398,
+    5580400,
+    5580402
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1940b9f398726b3606954bcc213f0c6a8a9486296ecef4590b177d4904a16c58
+oid sha256:a041379fbcecbbe3483948e4038ffbbe86d2dd49592285b4d283f3ad6341ffde
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa46b413cb251cb39123f169583bd8812070bef81217ddf3d27cb64d4aceb09
+oid sha256:f0ea6bfb7a26f0fdfadf45f28bb0dc7c5a3b2cc8a2495d5a56325d5b9d000e96
 size 4040701744