Run 4. Outer Step 15. Inner Step 78.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515419,
-    5515423,
-    5515426,
-    5515430,
-    5515434,
-    5515437
+    5515442,
+    5515445,
+    5515449,
+    5515452,
+    5515456,
+    5515459,
+    5515463
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 77,
+  "inner_step": 78,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45277733c521c277c5634bd7e9edbbbab5ee7accf63ed80d79ca24b60deb091
+oid sha256:e8f2f0e0da47fe98e233143110cf26bd41c1bb63f31a16afd8cebb02c4a0edc8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2cc5a7f33d67f0a0b6f24a6eb8234ca38dd5111c51799ba9deabdf8d5a7c68
+oid sha256:1df029b1cb01393daecb8135db60a12dbee8154bf88545bbe308308e8166f66e
 size 4040701744