Run 4. Outer Step 33. Inner Step 19.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544638,
-    5544642,
-    5544644,
-    5544647,
-    5544649,
-    5544652,
-    5544655,
-    5544657,
-    5544659,
-    5544660
+    5544662,
+    5544665,
+    5544668,
+    5544670,
+    5544672
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e27156c29762069b6177b135aac8f56d4c6113969143b2cf1d7886dc16470d3
+oid sha256:a76a0ad70d9a4a303950c5d84c6c62fd4b38a450ff13ee6f599e70da097cc7fc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9074b9756c698c5d194c3ba16c9c08a91713b4d12eb156803527f74fe20ff43
+oid sha256:5605a07f1d4ed1c942df46f58ac65266500f813491aa6dd9f394827d49bef05c
 size 4040701744