Run 4. Outer Step 54. Inner Step 89.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580252,
-    5580254,
-    5580256,
-    5580260,
-    5580263,
-    5580265,
-    5580267
+    5580269,
+    5580272,
+    5580273,
+    5580276,
+    5580280
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 88,
+  "inner_step": 89,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62caaecbd716a108f2339b0c49cf0a20a7213f606c7ef772d6e8973d13f642b
+oid sha256:e50e635c524c881820854e62176e1fa54b19d35549ce43b01b79706c0d8b90ed
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbd40980388c51ed3272ee97754054809ce317a5e209abb8750926a0b7c6aad
+oid sha256:c9d1c5bff9cb34961b1b0398f542e0a9e6f4f7409ea41fc8cb9658d5f1cfa665
 size 4040701744