Run 4. Outer Step 57. Inner Step 39.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602081,
-    5602084,
-    5602086,
-    5602089,
-    5602091,
-    5602093,
-    5602095
+    5602098,
+    5602100,
+    5602103,
+    5602105,
+    5602106
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "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 sha256:27a3de3a536ad4e865aa57734abf7741ef65e67302195cfa8e8b66cc52bd731f
+oid sha256:dd5633752dbc2520c73af3d56327ac3eb085758c240e707f07c828b34ae8c4b6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcba80b510ff2e36311a647f186591d5ace5b27de935d59442ca1db3603fe0c
+oid sha256:29fcdc2d2eb4a18eae1305394fb5205224200e959956bd11b24ba05b71d8cfa0
 size 4040701744