Run 4. Outer Step 66. Inner Step 92.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621702,
-    5621706,
-    5621710,
-    5621714,
-    5621718
+    5621723,
+    5621727,
+    5621731,
+    5621735,
+    5621739
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f9fc44a6fe136fe848c548ac4b71e942032de0218d88996ee5066539cd78a3
+oid sha256:573b50034b09b26957adeff42679da15f55ba5092fcac441c486e44dc2bc639c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408adc87294511943bf4e1571630de6ffd70c78f80aa6222e90850d2b26bd6f3
+oid sha256:5a2cebb53c442bf49f88d8791ebd6e9bb83f61a23a1ed7f14f2ec774a1f789d7
 size 4040701744