Run 4. Outer Step 54. Inner Step 84.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580065,
-    5580067,
-    5580069,
-    5580071,
-    5580074,
-    5580076,
-    5580078,
-    5580080,
-    5580081
+    5580084,
+    5580087,
+    5580089,
+    5580092,
+    5580094
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 83,
+  "inner_step": 84,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed07d6d429f3fc1861add1721eb99cee6bbdd88a2b14f55f198a573638ec2a1e
+oid sha256:59ca5b2026cd3fd396a40fefc2f93fa82274e9d5986bb730d39a4067490a3d43
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78de4664fd717e60ad9050372602b7e1f25dab2bf63cced0cb6d57aedd73a797
+oid sha256:f4c0a1520fd54a9f3853f3d5d2c81df05d4e09e1ad6ba9421c22901dc606dcb8
 size 4040701744