Outer Step 1. Inner Step 90. Batch Size 472

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "kmaheerminor/minor21",
   "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": [
-    5064186,
-    5064190,
-    5064193,
-    5064197,
-    5064201
+    5064264,
+    5064268,
+    5064272,
+    5064276,
+    5064280
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 88,
+  "inner_step": 90,
   "inner_steps": 0,
   "last_allreduce_block": 5063053,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d0a0e8932cb6e9c9b4c680b093d1452de6a81f910404ffd72203c8b6ad8607
+oid sha256:1a15bc234665b7a0551c6518c75f53b0dfbea3fecc62bd08dd015362c64e7881
 size 4040701744