Outer Step 0. Inner Step 27. Batch Size 416

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5142823,
-    5142828,
-    5142835,
-    5142843,
-    5142848
+    5142862,
+    5142869,
+    5142877,
+    5142883,
+    5142894
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ca8f7ec01f17cd0735aecd7d6c0eb9d50742ba5b3ba20e843d5aeeb86da84b
+oid sha256:e13b0c63fe152205797ef552785bb88b095f5a665b17f6685a7b39db01915590
 size 4040701744