Outer Step 1. Inner Step 428. Batch Size 400

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "kmaheerminor/minor15",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5146715,
-    5146719,
-    5146723,
-    5146727,
-    5146731,
-    5146735,
-    5146739,
-    5146742,
-    5146746,
-    5146750
+    5146821,
+    5146825,
+    5146829,
+    5146833,
+    5146837,
+    5146841,
+    5146845,
+    5146849,
+    5146852,
+    5146856
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 423,
+  "inner_step": 428,
   "inner_steps": 0,
   "last_allreduce_block": 5143202,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3917755e3fe251dc65a3b1fcc57145ceaaf0524a1da94b05a9b3bc962442d287
+oid sha256:c66f527413b335e098abf65e3424d76b79f91a91e90135b1fb2e9639b7cc61b5
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68744488b5af9d69e9f7343747b930eb7211ef6c33f413fa74966375476abedb
+oid sha256:6d725d6c79817ef7917cbf2e93a32c62126a6f5c4df19c505dd63848a40e4fab
 size 4040701744