Run 4. Outer Step 57. Inner Step 35.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601984,
-    5601986,
-    5601990,
-    5601992,
-    5601994,
-    5601995,
-    5601997
+    5601999,
+    5602001,
+    5602004,
+    5602006,
+    5602008
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "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 sha256:4041304dbc27d91c89756a64a72e0cbb5c90bc22692a5e94771acc5080ea33da
+oid sha256:50c01fa2a880d9c97162b95925c93d795b2132d5937daceabc3769876ea72d9c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab50c94941ada6ac3c24c1a27d614cb69634947d73454f80fa67a60217745cb
+oid sha256:133d32134e783ad289cd62d96f637212977b9b06e12ec0d784bb91765230860e
 size 4040701744