Run 4. Outer Step 18. Inner Step 29.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521924,
-    5521927,
-    5521931,
-    5521935,
-    5521939,
-    5521943
+    5521947,
+    5521951,
+    5521954,
+    5521958,
+    5521961,
+    5521965
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aec72ce93a166e7953b810901056b1d11106a0a4a069eb7d783d0b4b32cf58f
+oid sha256:fffc44d6f2d65c770fed90400fbf183d72131b059325525dfa20567926cd7b79
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1188483c5d514ccec77a4c3d768227f022856ab5bec10af2b298a676095490
+oid sha256:f43b14717cfdcb7b6b1a1398df34bc9d834f9228d88cf89a7cd7f22a1e653bfc
 size 4040701744