Run 4. Outer Step 54. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580185,
-    5580189,
-    5580194,
-    5580199,
-    5580203
+    5580209,
+    5580213,
+    5580217,
+    5580222,
+    5580226
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f2392a67c81454df87aca05c331efa5609ffd1f598e8b32b5b324962ef01ae
+oid sha256:2910783b8bcd06b0f341a3893cc4419f4c0c595a8d5eb397e12075f546588eb5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a602dae1277edd0b8778180962e116c43c78de79991e1855460f0850b9fae179
+oid sha256:7466de3dc80ea158208d5c2b01e7882c93c66e0af12390672c666141911d0a42
 size 4040701744