Run 4. Outer Step 33. Inner Step 17.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544580,
-    5544582,
-    5544584,
-    5544585,
-    5544586,
-    5544587,
-    5544588,
-    5544591,
-    5544594,
-    5544596,
-    5544600
+    5544603,
+    5544604,
+    5544609,
+    5544611,
+    5544613
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980ec67614e9371f2501a3d119f65020e5635a0a64777394092595e40eb418a1
+oid sha256:21907bd872336f45d51bb9654e48cc8814b5b3a447d77d978602cc8d952ea8f1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507198e05154334c7cb38a7eececf51eb527af11d34aaf939988e5baaa7b1a61
+oid sha256:3c0e5dcdfa0b365dff086fb0d72b32bcc2601f2d3aa4deed9fd48d839d30f237
 size 4040701744