Run 4. Outer Step 58. Inner Step 6.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5587647,
-    5587652,
-    5587654,
-    5587657,
-    5587660
+    5587663,
+    5587666,
+    5587669,
+    5587672,
+    5587675,
+    5587677
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae85720145f96d03630ca7f3a621c23fbd9deb7900cef6c1f471e30d450d4d13
+oid sha256:6748b1f8724626ebd68a30910ac19e68e75f40b8dd640ad95dda3cf982a8b8e8
 size 8081782439

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9096b09ce2e9f66e1771d37465fb608a592f8e1e4e71f5a9fb1038d1d9a220a5
+oid sha256:f94606a6e3cbd08083318deeaf53849aba595c378727353436da5f39c2627506
 size 4040701744