Run 4. Outer Step 57. Inner Step 35.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601970,
-    5601973,
-    5601976,
-    5601978,
-    5601980,
-    5601983
+    5601986,
+    5601988,
+    5601989,
+    5601991,
+    5601992
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7414a12798432e3438b6d3a5e6745ae71192375bd9f3744e639278d8075e6c23
+oid sha256:b83df131daf24484a34e76d963cb969dbac40a9bdd8c5f8d6fed179878cda6ec
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383f09b644f24e95ff101a5d5460c97aff8c768735da04b6620af976f7066863
+oid sha256:86c4c00adc5912611b8c88c9afcd1db2614bb4f162d74ec1a3a52d239f338f0f
 size 4040701744