Run 4. Outer Step 97. Inner Step 2.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "zeras141a/d8",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5691720,
-    5691735
+    5691742,
+    5691760
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5686307,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33967382c667c1e69a47b71b6b901b10dfcf40954e2e0f332a270e696df6ed8a
+oid sha256:7ecf5e6a06d68b4acd259085121877f8c38d49f1237cb196319f1cb3d0907f7d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ef1acca48fb7f5b32918747a12f8a1ec12d339bd02ad299af7be2b3bc1f082
+oid sha256:932dfb09bde857700b52900ca0fbe518f0eb674923f6fc4fb449d11f14af2851
 size 4040701744