Run 4. Outer Step 54. Inner Step 96.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580412,
-    5580415,
-    5580418,
-    5580420,
-    5580422,
-    5580425
+    5580428,
+    5580431,
+    5580434,
+    5580436,
+    5580439
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b372a7da4143aabd27d4244b5bbe32098af1783f4e6a19f0408e959b8b9c9f21
+oid sha256:2f36c9c75eecc7349d19ab7c7160b95e4914a9026740cca1f45cc07c2b1617c6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a59f14d69d3d0bbee3cbe4b8818249d1196a27086654225c3801e647d73916
+oid sha256:c022169fe15a93e3ea05b2703869a913f44ba81b9858ede995748d25cdd6025b
 size 4040701744