Run 4. Outer Step 96. Inner Step 39.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "zeras141a/d7",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "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": [
-    5691476,
-    5691495
+    5691492,
+    5691508
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 39,
   "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 sha256:748f0f55ad7b37846b76fb240fb3d712fd26d5fc06fb73922619fb8a676ce8e0
+oid sha256:95524da67a78b88d8830b6dcb3057ae42eb754756a3d2d2cf87139a31bbfdbc2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3812e38087f3e131519b09f2afa709607d618e57e52c39f4cc57449c29e60685
+oid sha256:1599dc808e3fbd84663b1bed2a684c039bac5c5e049d9a7b7b4f0f6cc6aceb51
 size 4040701744