Run 4. Outer Step 66. Inner Step 95.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621784,
-    5621787,
-    5621791,
-    5621794,
-    5621798
+    5621805,
+    5621808,
+    5621812,
+    5621816,
+    5621820
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 94,
+  "inner_step": 95,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e52fb7a73a6388d733423f01662c7d7b8fb912a8515323c31d64cb23b805968
+oid sha256:bb02adfe6986862adb1ca0ae821a91130bb25f8e80a762c24253f1091fc4a633
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a16d1fd9ba7f737b3cc6851c9d05472ac4f38c071daf91825c3a8f45b1349b
+oid sha256:18d91f941ca3859172bd7e95e27860bea11a89a7854435f09b36a99f3c91eb92
 size 4040701744