Outer Step 1. Inner Step 2698. Batch Size 348

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5186588,
-    5186649,
-    5186653,
-    5186658,
-    5186663,
-    5186668,
-    5186673,
-    5186678,
-    5186683,
-    5186688
+    5186726,
+    5186731,
+    5186737,
+    5186742,
+    5186747,
+    5186752,
+    5186758,
+    5186763,
+    5186768,
+    5186773
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2689,
+  "inner_step": 2698,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36939acc8415fd917fd44bb6dfce42742fee85080fd27fd8766e08de7d73884
+oid sha256:e17edb98080a27fd8b3e438651225004c1d35e9966c26ea4af7a6c5c850f87c8
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e9dc2a350f22e5282bf70b7052dc56b6e5da14a2d88f959f4775162b5e7c70b
+oid sha256:2dd1c54aa628ebdd95ee1b3a68bc5ba23dd6838186d4e950379d2dc5107f42cb
 size 4040701744