Run 4. Outer Step 57. Inner Step 31.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601806,
-    5601810,
-    5601815,
-    5601819,
-    5601824
+    5601829,
+    5601834,
+    5601838,
+    5601842,
+    5601846
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3cb087b58d6607a3fb69f89847a527364992d1b20128b0a02659e2dc406465
+oid sha256:bbb1b66170d3362222a6d20180cadea13d0e56a265fedf0a0609c7a59df8a0ed
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8518ff2ba551d6c9421c740268bdc331b0507ca89c150e21b95a945e49e3c187
+oid sha256:8a0c99bf7debdb8d46fa9b570cc0a8a87ab82553f8e5832b24e90777eb54119f
 size 4040701744