Run 4. Outer Step 62. Inner Step 21.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611320,
-    5611324,
-    5611328,
-    5611332,
-    5611336,
-    5611340
+    5611345,
+    5611349,
+    5611353,
+    5611357,
+    5611360,
+    5611366
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffc158dd8676d3506868165165fc74a6d404e3d844de7c9d22a4d8c3265cd902
+oid sha256:bdc3b725e2a8ee5e3555116028979fa1621b2fc039a3bb871d71ded91453b41a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f15c9183aee5d376ddb4888a376f6ab13865397825d7879cdbfc21d36d9d8cc
+oid sha256:61c831b12002b68354cdf66ec88bb52eaa007273d5293b9bca1eed29494a9e6c
 size 4040701744