Run 4. Outer Step 53. Inner Step 21.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "philip324mark/mark16",
   "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": [
-    5630883,
-    5630911
+    5631036,
+    5631064
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5630301,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795c6262989456cb1dc39b35dd1ed4aaa03f2c6a23afe1229ba7501ec20a538d
+oid sha256:bded4e3a62c4071ba7c6d458ad9275b8ab99fb3f58ed87812dbbda3b77fe68d0
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5520dd5ef40da57fc7f82cc611361c0665633e71ea6b58ed8adbd0a2e5090d23
+oid sha256:b5c136ed14b23301a2b7419a15e0f71e805491eaf1fd63049d552f3fd474ff35
 size 4040701744