Run 4. Outer Step 52. Inner Step 36.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576093,
-    5576096,
-    5576099,
-    5576101,
-    5576103
+    5576106,
+    5576108,
+    5576111,
+    5576113,
+    5576116,
+    5576118,
+    5576121
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e38a8612302b28e4b931f7c16e39ce6bab88b6d1fbfb832bc3a83a87178daf0
+oid sha256:a32f2a5eb33e4c8443a392df0d4a72a2ded6539dbe467d3727c3ec7e061842d6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2da0ddd52871b78cd03852c31c913a1d9bae8365e76ea21474305b1f97736b6
+oid sha256:99d37b7832eeac14d4a504e6fdde863c2966ce8e3a1580608bbfd2ea59eb2617
 size 4040701744