Run 4. Outer Step 37. Inner Step 58.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5552485,
-    5552489,
-    5552492,
-    5552496,
-    5552501
+    5552506,
+    5552510,
+    5552514,
+    5552518,
+    5552523
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 58,
   "inner_steps": 0,
   "last_allreduce_block": 5550793,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778948686589659615763309cc71c048bdb36bcaa97bc28b716b065d8282d912
+oid sha256:c5451fbd0ac3891dc0eaa1d83bd634ec77c1f6247d1c26ea1d1b4ae4054cff7b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d78011bbcb197f2779dc446093e8803b3cdf9aec4f6ae533dd020d45e68da32
+oid sha256:cfb4bc1b072143e2f1c988d49e88636ff2b506c5f0d13c960b2d6bda71ce569c
 size 4040701744