Run 4. Outer Step 29. Inner Step 16.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539593,
-    5539595,
-    5539598,
-    5539601,
-    5539604
+    5539607,
+    5539610,
+    5539612,
+    5539614,
+    5539615,
+    5539617,
+    5539619,
+    5539621,
+    5539623,
+    5539626
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c33fb95870f5315aa790b3348651fce7425421ad3c3a7ebaebb8915a993a98
+oid sha256:a2e11c7b3ad5d98f63c25f441c1244773f4454c48b0ab8ceb5069adc2f06f935
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9faf90354a7582c838c8b76563a33c2dfa897451a51c69c53c70ab75a849f36
+oid sha256:1379e89a86d422a5733d28f568e79b3894f5e813b4e73f050c127dbd4e064b10
 size 4040701744