Run 4. Outer Step 66. Inner Step 93.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621723,
-    5621727,
-    5621731,
-    5621735,
-    5621739
+    5621743,
+    5621747,
+    5621751,
+    5621754,
+    5621758
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573b50034b09b26957adeff42679da15f55ba5092fcac441c486e44dc2bc639c
+oid sha256:2d30048e0c19aa89bb594306e02d67a6f6a09c7bbf364df5d5fa9079bfdbe609
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a2cebb53c442bf49f88d8791ebd6e9bb83f61a23a1ed7f14f2ec774a1f789d7
+oid sha256:4a23fa99e7882703c0683decc5b6b32e355b02f5c5d2e7dfcd9f3869e276e2b3
 size 4040701744