Outer Step 2. Inner Step 558. Batch Size 120

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5080815,
-    5080822,
-    5080831,
-    5080841,
-    5080854
+    5080879,
+    5080891,
+    5080903,
+    5080909,
+    5080914
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 554,
+  "inner_step": 558,
   "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:c317991ec8ec7dcd81919e94a304c3a4e7caf062ba5aa48091d51ccfb7b407c7
+oid sha256:169f6d90575b9ddad8cb31c05887578b88b85208222c74d67be9dc3660b9df23
 size 4040701744