Run 4. Outer Step 53. Inner Step 123.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5589422,
-    5589426,
-    5589430,
-    5589434,
-    5589438
+    5589444,
+    5589448,
+    5589452,
+    5589456,
+    5589460
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 122,
+  "inner_step": 123,
   "inner_steps": 0,
   "last_allreduce_block": 5563454,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4af9146928a3667d3d55cdab01f155bf9640b029a36ff7d3937876975136714
+oid sha256:d9fcf8efc12422ac5db3eaf8060fd3dbffca70c45deccc8c4ad6bbf7a8ecf334
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd5ffb6eb331b51ebd9811716723f64cac8558a96b8f9a58cea0e0a9e897bbcc
+oid sha256:ff7669abdff60a58cb5c888f86b7f4e92ed666749ad308e1fe73bc03e760fd7f
 size 4040701744