Run 4. Outer Step 38. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5553849,
-    5553854,
-    5553858,
-    5553863,
-    5553868
+    5553873,
+    5553877,
+    5553882,
+    5553887,
+    5553892
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c10770ecfc2c98a15b3499b25b9be3d818e34bc40646cdc7dd1ea6502006d0
+oid sha256:13b20fe299622abd7ea1fef214cadcc73829ce877240e443978f7f7a9a49fe71
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6c67cc2c2e0a4d89825fecc94191dcf39cea7438a17d91a78705926c888a90
+oid sha256:d1d0cedf279e65d8c565e4df556d5c5a33f6c2803240fc78af27e2e4246a40fd
 size 4040701744