Run 4. Outer Step 66. Inner Step 97.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621999,
-    5622003,
-    5622008,
-    5622012,
-    5622016
+    5622021,
+    5622025,
+    5622029,
+    5622033,
+    5622038
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 96,
+  "inner_step": 97,
   "inner_steps": 0,
   "last_allreduce_block": 5613899,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e81ddae99686f4f4635c04ab968819cf7c2dfbebbd7120966c51b45ab3d8248
+oid sha256:df6bef4c217469ff17d0ac0c08af31813a8aabf4d91c2c91e69a60d1c43ee4df
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da2f2a0646bb4170f50af481cf41cb47174bf278eb85b74f3c42fac8cdf1656
+oid sha256:aae86fba2b0ed27da22538af77fdeb227f7d78c381934c2dc4035239bd78f576
 size 4040701744