Run 4. Outer Step 33. Inner Step 86.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546729,
-    5546734,
-    5546738,
-    5546743,
-    5546748
+    5546753,
+    5546757,
+    5546762,
+    5546767,
+    5546771
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 85,
+  "inner_step": 86,
   "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 sha256:851fdcd430202534477e5bab3ab4c5a70a6656322524e1629daf7f82865f4fd8
+oid sha256:ba6109a0eb9bae8a17874cd29c782bd0b12d1cec6f6050e192f660f85a1033d6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d73db1bc8b044dab4fcd2667ac9141835daa126eb9de3d3b126b5eff70164a4
+oid sha256:119787e25ed0441fead331cd1452884960d1737bbb23381d0991973eaf00a219
 size 4040701744