Run 4. Outer Step 57. Inner Step 33.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601913,
-    5601914,
-    5601916,
-    5601918,
-    5601919,
-    5601921,
-    5601924,
-    5601926
+    5601928,
+    5601930,
+    5601932,
+    5601933,
+    5601937
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "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 sha256:7903985b061d41701eb5323b539c6e66fa4708952359ce5cb33c5d80380b8342
+oid sha256:d3f78b812c336b5d274d587ba39c4b0c1a289500ff1941bcf048558c8d4ae463
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:315d7ae9dcd8d059aedad05aec3555d14f533153cf94b168f447d30f3b42b887
+oid sha256:e739afcfe299477401f67bd8dd8d562a730ae5538025bb4ac9333951c962f47b
 size 4040701744