Run 4. Outer Step 61. Inner Step 61.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642731,
-    5642736,
-    5642740,
-    5642745,
-    5642749
+    5642753,
+    5642757,
+    5642761,
+    5642766,
+    5642770
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 61,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab5dad4b55e989e041a0247451960b78a6135ccdc5063f4b8c7a13aa495631fa
+oid sha256:d643c80178dcff0703eacba4645a13f840885470645c9663393503af75b9682c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf9d17d53152b522300ec8624dbcee9b618afa488b4dd49ef66e38301b48ebd
+oid sha256:28b411a5e62b4b2212ec80f568c95e893657bb28bc4781210b7330f4d2371886
 size 4040701744