Run 4. Outer Step 54. Inner Step 92.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580316,
-    5580319,
-    5580321,
-    5580324,
-    5580326,
-    5580327,
-    5580331
+    5580334,
+    5580336,
+    5580337,
+    5580338,
+    5580339
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "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 sha256:4a26b928bec2e57f90f157f45e504d463ff3d5e3e4cdcf7b3d6fa0b8923ca1b0
+oid sha256:255379d10754ec1f891caf2c2265907aecf8c7c2c57a76082d3826e32f8cb26f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317272d4929190c5c93a312f8f66391cbbbdac8778ba3c5a6bd1b013885daafb
+oid sha256:e65cadc9136f30e3e362c0a888f211b299e030460eaad74e32520b6a3d768afd
 size 4040701744