Run 4. Outer Step 95. Inner Step 35.

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": [
-    5690309,
-    5690326
+    5690338,
+    5690357
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 44,
+  "inner_step": 35,
   "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 sha256:21abf23257483c8b59c1c8bf4ce856735f04515cd14e5e5e8231307597f9e94e
+oid sha256:c4fe42b6c687f6f3a2d60162bc38c830ed903dbee5c10abf0c5a0962a196b959
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20badda8540bd4f51137a8f2d6d22759cf987bf94fd9bb232577e25c2f4e10a
+oid sha256:3f6ee04ff6318a14e0a801eaabd17264b363f1c97477720b2a9d08b18153bae7
 size 4040701744