Run 4. Outer Step 3. Inner Step 131.

config.json

@@ -268,18 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484621,
-    5484623,
-    5484626,
-    5484627,
-    5484629
+    5484633,
+    5484636,
+    5484639,
+    5484640,
+    5484643,
+    5484645,
+    5484646,
+    5484647,
+    5484647,
+    5484648,
+    5484650,
+    5484652,
+    5484654
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 130,
+  "inner_step": 131,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63155703da0dfb7cb553076541260e54071605a08f922f9bd74bfef9f5309d60
+oid sha256:bb2244f93f218531cee684858f2962a4d935f91bf41eb3b1d756cdf13e99567c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c2b8ba5c9cb6a36724ea37785dd29e4aad6f3b641bdb667be9f136640091d8
+oid sha256:76bca748a708b1740b4c60edfaacf597e24bdab2f2c444220824f42eacc8436b
 size 4040701744