Outer Step 0. Inner Step 807. Batch Size 456

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5055255,
-    5055260,
-    5055264,
-    5055268,
-    5055273
+    5055299,
+    5055303,
+    5055308,
+    5055313,
+    5055318
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 802,
+  "inner_step": 807,
   "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 sha256:61998131a3b2175e918368bcffec2461c8a07f7ca55adfb8f6728b5bfc02458d
+oid sha256:6cc4f555e6fdb4ec485915a54ae81c1d981f78b0fe5e1b1696d96d0e8d8af2e9
 size 4040701744