Outer Step 0. Inner Step 213. Batch Size 92

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132658,
-    5132662,
-    5132666,
-    5132670,
-    5132675,
-    5132680,
-    5132684,
-    5132687,
-    5132694,
-    5132698
+    5132728,
+    5132734,
+    5132739,
+    5132743,
+    5132749,
+    5132755,
+    5132759,
+    5132765,
+    5132775,
+    5132783
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 203,
+  "inner_step": 213,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04c6f6e50c225ac71a82ad48751744dd25f6c4058b9b97e852b8f046526a8d3
+oid sha256:1b3cef113e7b875a075fc902291388f05b46718bd8a6cd6005898493faf7de7a
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52409abc02c418e99f053cff6dd66ac0094c3aaa66f594ed256241a7009d97a5
+oid sha256:9072073c7cca8470bd543033194e753e8ed80436f348005117d6454c439ae034
 size 4040701744