Run 4. Outer Step 52. Inner Step 39.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576189,
-    5576191,
-    5576193,
-    5576195,
-    5576198,
-    5576200,
-    5576202,
-    5576206
+    5576209,
+    5576211,
+    5576213,
+    5576216,
+    5576219
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f267c08c60a33efae4754f56ce6a570a5df68111a24c67d7d6c6c97870a5549
+oid sha256:ae1a4dfb69810786258b47c03162c8b4c72dd160a5ffa4ae7e0a1826e470565c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aaa307967baf2f81c8cddcc16264006c812e9e575bd618e660fcc8f8ad8b616
+oid sha256:936fd9e980a84e8e06bf2a2caab8f9ea341e79b215a64d8b730dbbc32fa43518
 size 4040701744