Run 4. Outer Step 58. Inner Step 13.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5587468,
-    5587471,
-    5587474,
-    5587477,
-    5587480,
-    5587483
+    5587486,
+    5587489,
+    5587492,
+    5587498,
+    5587501
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a68914465a785c5b41850abee99e18a7988ad0087ef976d0754889831bd1c5
+oid sha256:65780e76930bd06c569ec5a4493e872418dfbeaa6c949c0f6ca272112a7a7619
 size 8081782439

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b701b1442f7893214e2c44890f32362aad986bee8f85efbd0bf92620761115
+oid sha256:ccc94e9d1750fc7004d592e5ffe8988e7ff611b862c50b6eb5c119e1955a9f2d
 size 4040701744