Outer Step 2. Inner Step 333. Batch Size 264

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5075494,
-    5075501,
-    5075507,
-    5075516,
-    5075521
+    5075536,
+    5075542,
+    5075548,
+    5075559,
+    5075563
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 329,
+  "inner_step": 333,
   "inner_steps": 0,
   "last_allreduce_block": 5063053,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03290b3bb3c30aadd9e238abbff624a9cfd45a8b3b09b3fb86c9417789e2d1a0
+oid sha256:d98e94d04ba9be26ef9a8786a539257709b2c7ece3d45a73ac400cc28a6159f9
 size 4040701744