Run 3. Outer Step 9. Inner Step 29.

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
+    5399717,
+    5399720,
+    5399723,
+    5399726,
+    5399730
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 29,
   "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 sha256:8d2da96bb940c970f4df581a001a121102c0fa2822a194bb93f9ecd3a779794c
+oid sha256:6942cc0f849dc6aab0c81db0cd0739c6873bffff4b0c5a696f99b428fde90ddb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e688b68fcd1587bb95958dea11f8b434e79ca426cecc78f3100ebb69f23303f
+oid sha256:d4f3903c9d3b2e5ddb31b8ab567cd34082a146c57f961b2b19d63377d36ea50f
 size 4040701744