Run 4. Outer Step 60. Inner Step 29.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608052,
-    5608056,
-    5608060,
-    5608064,
-    5608068,
-    5608072
+    5608076,
+    5608080,
+    5608084,
+    5608088,
+    5608092,
+    5608096
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8a0b31e288170fc8ff8109e04e5ca8005ca9ef16749d3bbe280bc125827b64
+oid sha256:34ceb8c6ac7f7fa88777387c377554c6cfaf3da0cdfb8d978d4ed1352139cd1f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042994391bd74c8a571517c8d36a610e256e34d05a1f5b93097d6e37477e134f
+oid sha256:f67d9ac5fcdada86cde8147d9392778add8105630313fd01f47ceefd839bf902
 size 4040701744