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/d8",
   "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": [
-    5691510,
-    5691523
+    5691518,
+    5691538
   ],
   "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": 5686307,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818cbcc90d4834d88d402af0b108f1a440ff95a005c098d611d36e9749bf11cc
+oid sha256:e72cdb3539e55cadcc80df45a06e34d5491b29a8bb5771ab8b43373a30f11891
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce442906ef82aea71703f0b2c76568b66679f68fbf2b1fd66a5472862176f1d
+oid sha256:44732e4a15a1fbd11e6d1c0362e52f19759cb2a42c20bb0b50e703e2b66904d2
 size 4040701744