Run 4. Outer Step 22. Inner Step 1.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "jonna32/mainnet1",
   "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": [
-    5528392,
-    5528396,
-    5528400,
-    5528405,
-    5528409
+    5528468,
+    5528472,
+    5528476,
+    5528480,
+    5528484
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5526620,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935c3dff2b1093478886e227edb068922c9b08089e6f0901cf43221e96d7fb48
+oid sha256:16f71712cb35f08e0c9858d5d3c813577d3707de7b0afaedf10b63ebd088ca85
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a8f299c0e91e8c87bd203e69e6557d72f4fe93cf7700cf596457cb73af98bc
+oid sha256:65f21d27c8b1c717e0dcadd693d60d482744666321f7db4b5b5ad8680f3fb7fe
 size 4040701744