Run 4. Outer Step 32. Inner Step 37.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543867,
-    5543872,
-    5543876,
-    5543881,
-    5543886
+    5543891,
+    5543896,
+    5543900,
+    5543906,
+    5543910
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bfbaf9f950cec0a62412610e611e5870bd336220ad73301b658f8bc1b5adf8
+oid sha256:de59d85a0f830ec3ad13f39abeeb068c8191b1119e272ef15e8a30a2be874364
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3fc11eb920b711f13136873102cfb238e76e70b20cf11c4ffb813dadbba34bb
+oid sha256:c83696832b1c3d483b9038e5d8f1f0026d4e2e39bebdd9074f7e7387725b5df4
 size 4040701744