Run 4. Outer Step 58. Inner Step 55.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604023,
-    5604028,
-    5604032,
-    5604037,
-    5604042,
-    5604046
+    5604051,
+    5604056,
+    5604060,
+    5604064,
+    5604068,
+    5604072
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 54,
+  "inner_step": 55,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceed35703e662ab6aa49ffcfd4a295dd20353b87922b673d6faafd5540356311
+oid sha256:0bbd8c38d6271194c3765784b0a5cf77f1152701efd3948883ba2d683f2c0ecc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c05d827bd0a24122087d917650a29c358555cbc22fd94c2fd691e717da90718
+oid sha256:c5f3607da11d68dca31662a949251d390c57538537ebd8dbd325a1558c519947
 size 4040701744