Run 4. Outer Step 95. Inner Step 34.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "zeras141a/d9",
   "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": [
-    5690321,
-    5690336
+    5690356,
+    5690376
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 43,
+  "inner_step": 34,
   "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 sha256:87baf8c6ac02cbae48078cc260a06b66fa360ac35385542b918dde09f40ca91c
+oid sha256:1aacc3e17e02575cfa4c255bda6e374b40966d785b42ca6ca4debb51f4731f6a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4973a44974568c9fb2f697c73cd5dcb390a430405372c0b7066391f137fc47d7
+oid sha256:669ff5bff795568ca81cecb38b1567b218084d537610a761a45d1de1f1222539
 size 4040701744