Outer Step 0. Inner Step 508. Batch Size 24

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5062949,
-    5062953,
-    5062957,
-    5062961,
-    5062965
+    5062984,
+    5062988,
+    5062993,
+    5062997,
+    5063001
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 503,
+  "inner_step": 508,
   "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:da7e39e72d7efb30a110c574e74927af9435b189d87564ef05df0c1bf8e9dda4
+oid sha256:cefa5a2333ce3be43b103cb1f23fc74ca42bac6b66cb563e10b2616576c37b9e
 size 4040701744