Outer Step 0. Inner Step 843. Batch Size 132

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5055547,
-    5055552,
-    5055557,
-    5055562,
-    5055567,
-    5055573
+    5055591,
+    5055596,
+    5055600,
+    5055606,
+    5055611
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 838,
+  "inner_step": 843,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742b9ce7d1267156b84f948b3c24c48dd1a58ea6f5d03904d149aa13710fb7fc
+oid sha256:9de31f9465edd42399bd77d98660c6a3992adc29ca18d419e3643583a4ad7a42
 size 4040701744