Run 4. Outer Step 61. Inner Step 7.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609022,
-    5609027,
-    5609031,
-    5609036,
-    5609041
+    5609046,
+    5609051,
+    5609056,
+    5609060,
+    5609064
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "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 sha256:822ef6f90d0ae746c70152519c519864418ba3ca38ceb58f43a84143f251838b
+oid sha256:b68beb748626ca1b619393f2b2ab627c246514f4835b9a0fe900a28a48d2c887
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee230569520907d763d373af7b576d44ad3562b7c321eb4bb714b7a456804b9b
+oid sha256:ec63342eddc493bfaed6b267dc28be8029a3133074832f52f9bb3b1725130099
 size 4040701744