Run 4. Outer Step 17. Inner Step 59.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520658,
-    5520661,
-    5520665,
-    5520669,
-    5520672,
-    5520676
+    5520680,
+    5520683,
+    5520687,
+    5520691,
+    5520694,
+    5520698
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 58,
+  "inner_step": 59,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45283d0e01932496cc84d3a08a9e89788bb9d80e4fe4b65989abc06004445be3
+oid sha256:40197afb367aad17025f092535c34b3fd14321162e276764cf15dd80b0309d38
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e541b5eb0e00cd3e6a1ac4aedf1cf8f9b1b4821f7f1cda18c983ec8a3a9f136
+oid sha256:6d85d88360d19c9b82098d040ca0092357248523c04161062ac8235632429dd4
 size 4040701744