Run 4. Outer Step 61. Inner Step 62.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642859,
-    5642889
+    5642919,
+    5642952
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 62,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c321843dd35fefccd8e37b95e76f36723f0973b703e351ae39b4474bcf5060
+oid sha256:bbc6b922588b380601ee0af3759dcf4cdae3d06d26549510b24b0377d7c33d5e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308481206b3b9fb21fa25d63e6b58d56e1e7baf791d528bb8ec2d2cc22274050
+oid sha256:23c97a08b57d6c5f9a972cc2661385332932f11f43458a84e8bb43d31b30a931
 size 4040701744