Outer Step 1. Inner Step 61. Batch Size 128

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5143898,
-    5143904,
-    5143910,
-    5143915,
-    5143922
+    5143940,
+    5143946,
+    5143951,
+    5143956,
+    5143964
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 61,
   "inner_steps": 0,
   "last_allreduce_block": 5143202,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a060667002c034f56e834e5b1507e18513f0b92de68fe14a0799c55c820edb06
+oid sha256:7128e9c7dd39cfeafa4e0fee2f7eedc10bbef54199817e2513de0c4b0072663a
 size 4040701744