Run 4. Outer Step 32. Inner Step 37.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543859,
-    5543861,
-    5543863,
-    5543864,
-    5543867,
-    5543870
+    5543873,
+    5543876,
+    5543879,
+    5543880,
+    5543883
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795be7f14981c466d8079e3f8fd7c2b0a193f22285be9a0d27128e56b111bc8b
+oid sha256:278fa955207bb8c68779282663df3d7533c90a833aa21cc4bdd93a502f0234cb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e48902c7ba3788bb5d2ef3ecdf77df6a2169722a76a46d47aa102e06ed156d
+oid sha256:48b1abc57605e8529b87b2ddb7010de841aeb44ab0497a9ecfea9a503e9bd583
 size 4040701744