Run 4. Outer Step 50. Inner Step 113.

config.json

@@ -268,15 +268,14 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5625171,
-    5625199
+    5625228
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 112,
+  "inner_step": 113,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2405c6a1f9f2627afd100d2ec646fc13d7bfa3d3d31fcc31a7bca360cd24d99f
+oid sha256:e829d562149ed15b5a8e50568a7f8ddd28d2634ed4833eabed30a70e46687c21
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9697b5ffc466514b7d2e12d6774db2018883df1a57a1771e9214bbd4bc9684
+oid sha256:5c389a96c2e2a8832b9cc4388c72f21b390baa541b8cfe529b7682b926ba2f5d
 size 4040701744