Run 4. Outer Step 33. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544250,
-    5544252,
-    5544254,
-    5544255,
-    5544257
+    5544258,
+    5544260,
+    5544261,
+    5544265,
+    5544268
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbf19696fbe26f26a34383322b0c57df973f8feaaa02db483af476b98bf6508
+oid sha256:3c4fd5f4543d431d77c3c8e48061bc14096097cc95daf50ce9e8f32db7b3245f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca37259fee42103909224877cf7f026d8ab8b6081fe09facca73fb64c7b4b080
+oid sha256:1f9b3827325f811765612a8621dddb62cc04686491be91091c51ca6b770987f7
 size 4040701744