Run 3. Outer Step 9. Inner Step 38.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "kmfoda/gpt2-1b-miner-1",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5399343,
-    5399347,
-    5399351,
-    5399356,
-    5399361
+    5399912,
+    5399915,
+    5399918,
+    5399921,
+    5399924
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4b19f27c57d8ecc261b154c403c8f80656214b475ef839662a7dd4ae39f156
+oid sha256:21a952a977a1d195ac37a23447e4c35367a0dc320782d4797a39d785b607d645
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e688b68fcd1587bb95958dea11f8b434e79ca426cecc78f3100ebb69f23303f
+oid sha256:e4acb7ff8ef4683416b90f25d37bd0b495b8a0e29faad15fa15b59ab59ee08f6
 size 4040701744