Run 4. Outer Step 96. Inner Step 32.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "zeras141a/d7",
   "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": [
-    5691587,
-    5691602
+    5691595,
+    5691616
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5690407,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d9ed2c2cdcefcc4dd5f7204371bca3c0239249df196c5f10935d448969455d
+oid sha256:ef30a3ab45171d78221045b9a88bb39b0ff5bd6fe839b88244de6ef2c11e6c82
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58151aba3e99f846e601ead3eb6d259ea93a546923c439cb5e6e0e84a8ab391a
+oid sha256:e4fc3938ffc6a74c4050e50ec68f58713aa0c4d015a7b6b62837fb2892a29fe6
 size 4040701744