Run 4. Outer Step 61. Inner Step 8.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609046,
-    5609051,
-    5609056,
-    5609060,
-    5609064
+    5609069,
+    5609073,
+    5609078,
+    5609082,
+    5609086,
+    5609091
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b68beb748626ca1b619393f2b2ab627c246514f4835b9a0fe900a28a48d2c887
+oid sha256:068c624b263e36c53c6045e37938e06c8b3e8ae5c1cc0349612aeba9ff48e209
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec63342eddc493bfaed6b267dc28be8029a3133074832f52f9bb3b1725130099
+oid sha256:8479d3e6b60ed81c17b8bdb498c07de988f1de96a73fbbc16c1af77223d223eb
 size 4040701744