Run 3. Outer Step 9. Inner Step 66.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5409799,
-    5409802,
-    5409804,
-    5409806,
-    5409808
+    5409838,
+    5409839,
+    5409841,
+    5409844,
+    5409846
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45588fbb87ad44ee16320a65d5c823a3cf5fb715da3cdff0a3b62f94cb75a3a
+oid sha256:8b5f033d199bd147bd644f19a3f5f5720457a48570cb6f0ec3c5a30ee6305c43
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e666d8aad060964a3c4a0441ce76cfd54774fe3fdd1bbfdf12a53af37024361f
+oid sha256:cacfacfd081a6d46c34f378081765d8fdd9f0347cdf86130394f1306a9653a2d
 size 4040701744