Run 4. Outer Step 54. Inner Step 90.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580257,
-    5580259,
-    5580261,
-    5580263,
-    5580265,
-    5580267,
-    5580269,
-    5580271,
-    5580273
+    5580276,
+    5580279,
+    5580282,
+    5580284,
+    5580286
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 89,
+  "inner_step": 90,
   "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 sha256:3780fd1560bbda023f2af572f45cd63795be47337c80a0c303cc44c01f1fbc23
+oid sha256:cab0b229a50594c397e0ddaaa6123d3eb1c9ea2a0e7009d6e3b23a27a425e1fd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625f8f66d43e61115a91a89df591e8d4a40f9bc3e3d78a72cf184ab5c97ceae4
+oid sha256:0d79d298b1e29fda879bd701a43f673d8501ab35f6bec16001be1e934a54853d
 size 4040701744