Run 4. Outer Step 75. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663122,
-    5663140
+    5663159,
+    5663180
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5662361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b60e10b3d09c54cc7d0ea919e7d1a775398ebf7ab8fcf0734e394aae86d585
+oid sha256:de9f439990dc095356ee242df455de6251c27b474d6e09a84daca82643089642
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4e7325abd765e884b788d0dddb03a8db56862f39fcb633fe8cb98182be56c3
+oid sha256:e10737361cea64be98b273244d4643c3b4a1920bd8d9322cb0ea579fff04b71d
 size 4040701744