Run 4. Outer Step 29. Inner Step 0.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539971,
-    5539975,
-    5539979,
-    5539984,
-    5539988
+    5540032,
+    5540036,
+    5540040,
+    5540044,
+    5540049
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a1c6f015ff65bf994345e51f02f67afd761a610c229197438683ad000ab72a
-size 8081782026
+oid sha256:920babb96081e44d6506454dc66e568c8362ef2cd470be8a608f93137e30f08f
+size 2944

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25be472c21830e4f192ad750635c35abc95edac813ab158a76856fd6f67825a2
+oid sha256:130bff7c6b3e2aa7641fb0c9596e4ecde06a35c863a3c2c10f634717c82ebef8
 size 4040701744