Run 4. Outer Step 62. Inner Step 8.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610954,
-    5610957,
-    5610961,
-    5610964,
-    5610968,
-    5610971
+    5610976,
+    5610979,
+    5610983,
+    5610986,
+    5610990
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3644917f69273935eda180bc6906c09fc23d0d4bfba4ddf9896dc7540deeee3b
+oid sha256:4c991928e14f03e61585afc19e6e2ea8dc3c9fba4928ad299cf0a5ae3782d7f6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f123b3e85e34ef971ad825e89a843f9c3d4ca6b499dba8dd7a981f64f6d6e70c
+oid sha256:515b3e7905662b75fd4a3f7165e107dbc06045383adf0742d2252767f641b2a0
 size 4040701744