Run 2. Outer Step 6. Inner Step 623.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5337954,
-    5337958,
-    5337962,
-    5337966,
-    5337970
+    5338001,
+    5338005,
+    5338009,
+    5338013,
+    5338018
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 617,
+  "inner_step": 623,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0e4a3891097442bec9885261337c76452694cf55632f164c435ce9bfba172d
+oid sha256:ff0b9d5406afa064b8511b76fc8fec7ed9a840d930f4967b28040d6dd03c7b9b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc6e92db01e91e4ec55eb3e1a8affb9f91e88cea5cd6d0764073afe21bfb88b
+oid sha256:3faf2cc21c614e56983efca6a45cc684d65f598cb3e9420d7c8f1383bce7add8
 size 4040701744