Run 4. Outer Step 66. Inner Step 102.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621969,
-    5621973,
-    5621977,
-    5621980,
-    5621985
+    5621990,
+    5621993,
+    5621996,
+    5622001,
+    5622005
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 101,
+  "inner_step": 102,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f9332ddc9d9e625f3fe47b66ba032c2fe646619e8380718af16151d0a75d6f
+oid sha256:32320a0ee45898ffe7533944940e647ca0fcb933e44ed5722ee6bdf81f0edd25
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa8dbfb9476778263a36ad655feb3c2d065ea97dfa15015d97492065880ef91
+oid sha256:fe6881b49ba1d7ba62cce34ddd5f830c838a5d7960df267886f376205a085bb2
 size 4040701744