Run 4. Outer Step 57. Inner Step 32.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601944,
-    5601948,
-    5601950,
-    5601954,
-    5601957
+    5601960,
+    5601962,
+    5601964,
+    5601966,
+    5601969
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3768701faa8fa1220f8a3095252588106c63fc5723ede42fee8e14cdfc15460b
+oid sha256:1e88d993db319561543adc0a0bc615815b41b3f7975ee74098821b1f416af4bd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87af110a1f73537b4f768227d41f3936e142a1d5d449592cec210cc4a34a284
+oid sha256:8f4ec2f6f79d622501be591a716f4d60172396dc9a08ff26ecd330e7dd37eeda
 size 4040701744