Run 4. Outer Step 60. Inner Step 23.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5640164,
-    5640200
+    5640235,
+    5640271
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3a7423dee5ceabaa07d54942365414a1ace3e9bc177ae4299bbad1ecb0739f
+oid sha256:9332355155f0171f0251b0c6686231aa496cf3d3d72273fa534937c4585e2b65
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c869fe6765ec65aa80aa9c77bf62b092f9ef890b90e1ed140aa8ca856bcad1
+oid sha256:540861c5e342f998810c0615fdb1de7aea18cadc6fa72a6478b4116a8bf09787
 size 4040701744