Run 4. Outer Step 96. Inner Step 39.

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": [
-    5691405,
-    5691421
+    5691429,
+    5691443
   ],
   "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": 5686307,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18859520c65f35e9ef1da9514293516b8e052f412fbdce71a6d91bf1e0f0b7e1
+oid sha256:fc08200eb831a3d09a545a830a414a04cdf13c05e618bfff514c05bed35a0826
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77531a247fd3baea00a44b4e5bc297f5e30ca71712569b557fa2e6aa2e8c30b
+oid sha256:9c15c002feef7eee01e9829bb54e4fbd0dca8d8fc01556cba0e90e6b486a3fd5
 size 4040701744