Run 4. Outer Step 57. Inner Step 34.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601956,
-    5601958,
-    5601961,
-    5601963,
-    5601965,
-    5601968
+    5601970,
+    5601972,
+    5601975,
+    5601978,
+    5601979
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232a77007c5436f73f8ca222298a749ccf45360381b2bedd4df6d4b8ef84b9bf
+oid sha256:4041304dbc27d91c89756a64a72e0cbb5c90bc22692a5e94771acc5080ea33da
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6da92059a88e15f45a2619d8d328995ff9da212b46f31c6bbcab4b2c98df123
+oid sha256:7ab50c94941ada6ac3c24c1a27d614cb69634947d73454f80fa67a60217745cb
 size 4040701744