Run 4. Outer Step 82. Inner Step 8.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5671739,
-    5671758
+    5671780,
+    5671800
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5671361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45cb7a67bfb33d559dadcc0606a10482c65d3debbeb3f28dd3ee46276330264
+oid sha256:62c49827cfb6831b048bcfed4fc60c92da9e1c4cec7bff6fc511dad5dd4ac4c9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91256e38e026a8412ceac2783c32b1be15cd8ccf01afa4fe50b54121afdba50d
+oid sha256:3a7c929500ef3054917305c8b38c166c4c6ac00dfe2e0fae06c12839e1a1129f
 size 4040701744