Run 4. Outer Step 54. Inner Step 93.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580341,
-    5580344,
-    5580347,
-    5580350,
-    5580353,
-    5580355
+    5580359,
+    5580362,
+    5580364,
+    5580366,
+    5580369
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "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 sha256:255379d10754ec1f891caf2c2265907aecf8c7c2c57a76082d3826e32f8cb26f
+oid sha256:0d58b0527a2b65278c06bcae10a33032890f3f46a33bb90335c938245b7802ed
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65cadc9136f30e3e362c0a888f211b299e030460eaad74e32520b6a3d768afd
+oid sha256:d7c70b0a6c44094c9be335954aca6f7b13aaeeb8eaf74a031f69dddcd1dd3ffe
 size 4040701744