Run 4. Outer Step 56. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5584018,
-    5584023,
-    5584027,
-    5584031,
-    5584035
+    5584039,
+    5584043,
+    5584047,
+    5584051,
+    5584056
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7f80a067f94763e06619151bf2f1a9c54bca9cb233fe5b2ee6a045b2320a59
+oid sha256:fb3754c3b5d53effb9750b8a4cdd7e657ee79ace67861c4f5749c837e27e49fb
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37df82deea48892fc3b143bea07b390b76f1371afff7df489a53e9d4338be02a
+oid sha256:6d231f4d45b0e5e3326618ecf2d74b8d202576b5d07e689f64f669610067de0b
 size 4040701744