Run 4. Outer Step 54. Inner Step 96.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580412,
-    5580414,
-    5580416,
-    5580419,
-    5580421
+    5580425,
+    5580427,
+    5580429,
+    5580430,
+    5580432,
+    5580434,
+    5580437,
+    5580439,
+    5580442
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "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:e66377a81c1cc71154795d217762e06ac624c010d2af3393a87c1ae7f32a29d9
+oid sha256:655cf618fb4314ea2d2abf58e16480d13f9d714f3dbb7824a122b22bb1d0771c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05de0c0a370f83cf8b11d4b1025e1dd1fd553fc6781f70ba13ff3e06851949fd
+oid sha256:53d4d2588b06d9d069bf597b100f2111b03ed2100c4dd17fd7cf28ecfcd96cd2
 size 4040701744