Run 4. Outer Step 54. Inner Step 135.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597898,
-    5597903,
-    5597907,
-    5597911,
-    5597915
+    5597920,
+    5597924,
+    5597928,
+    5597932,
+    5597936
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 134,
+  "inner_step": 135,
   "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 sha256:9296b2cf51a44d4ef4ff07e5081fc4dadf21be8de5ca320ee1541eb237df279a
+oid sha256:2af33e11a3ee18be0122d3723214bfb19d48fedea653f8d4da957cc46ea949a0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7584869f0a3aac560b01251d3ea59c169d14ea3c12670aebafe6bb21f119a2
+oid sha256:bdc1f3a842e920caa24e48697bf9634d8c9a0e99be8ccdf42aaaa4dc06905c3b
 size 4040701744