Run 4. Outer Step 96. Inner Step 43.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "zeras141a/d8",
+  "_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": [
-    5691518,
-    5691538
+    5691540,
+    5691554
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 43,
   "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:e72cdb3539e55cadcc80df45a06e34d5491b29a8bb5771ab8b43373a30f11891
+oid sha256:1464dd67363ab8a169bfa61615da109053442e29bda6e3b8d1649e9be0846a51
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44732e4a15a1fbd11e6d1c0362e52f19759cb2a42c20bb0b50e703e2b66904d2
+oid sha256:8243f784982661d4df8b3d9e4d1f0b53e8cc357f91e79656d657106eccfad684
 size 4040701744