Outer Step 1. Inner Step 129. Batch Size 336

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5144495,
-    5144500,
-    5144504,
-    5144508,
-    5144512,
-    5144517,
-    5144521,
-    5144525,
-    5144529,
-    5144534
+    5144566,
+    5144573,
+    5144579,
+    5144583,
+    5144590,
+    5144596,
+    5144603,
+    5144611,
+    5144619,
+    5144624
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 121,
+  "inner_step": 129,
   "inner_steps": 0,
   "last_allreduce_block": 5143202,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf906cdbe5917df74a1f5a8fea84635b4104e1af2f8424a56592c1ae1ed8ebd9
+oid sha256:ef914c12d050ad98402699087bb76a2de8a1faf950cc9194806c6d61518ba6c2
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6a6a95036df96912d7ec20ad8f4215a6e8d7c4a1231e30b746f86a0ec7934b
+oid sha256:08617e2f2edddf9b3b41777ccbd2030bd9c50c1ddde3d2101577a08a360fdb33
 size 4040701744