Run 4. Outer Step 50. Inner Step 2.

config.json

@@ -268,18 +268,37 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5622080,
-    5622104,
-    5622107,
-    5622109,
-    5622112
+    5622114,
+    5622117,
+    5622120,
+    5622122,
+    5622125,
+    5622127,
+    5622129,
+    5622131,
+    5622132,
+    5622135,
+    5622138,
+    5622140,
+    5622142,
+    5622144,
+    5622147,
+    5622149,
+    5622149,
+    5622152,
+    5622153,
+    5622156,
+    5622158,
+    5622160,
+    5622163,
+    5622167
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2a0cbd13d1df2fb67e6ed8feaa25aeaee68b7ee9840f2c8914b16ce6f3e484
+oid sha256:70ae539ed6fca7a73a6110d09c99437ea5337278f73f6c2fdd2d73ae0e7255a5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51896991661e02507298ba54890fd1fc262804a915cbfa14522803049877c769
+oid sha256:2fb490d5eaadec54bebdf9d7d5cc4e123fb6fd0bd02c60ebc1707abf3efb98c1
 size 4040701744