Run 4. Outer Step 95. Inner Step 16.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5689479,
-    5689505
+    5689533,
+    5689560
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5673692,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c4f66847ac3f78cd9b220e81432400d00bb07f02f82c1b77ea5299ec8d9878
+oid sha256:891844623d59a39e7a100c58bfad7598f80026651c8829d6e8980a6684930ab5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754b66cbce876e58aa938c8c8ad1d64122a4c1caa6cb8d36d2ccfafba203642a
+oid sha256:1273d82f411e2b7169594cbc3b6ab8c2d264d1e53bea8919d6f502a1fe05be0a
 size 4040701744