Run 4. Outer Step 50. Inner Step 4.

config.json

@@ -268,33 +268,31 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571714,
-    5571715,
-    5571716,
-    5571717,
-    5571718,
-    5571719,
-    5571720,
-    5571722,
-    5571723,
-    5571725,
-    5571726,
-    5571728,
-    5571729,
-    5571730,
-    5571731,
-    5571732,
-    5571734,
-    5571735,
-    5571737,
-    5571738
+    5571740,
+    5571742,
+    5571744,
+    5571745,
+    5571746,
+    5571747,
+    5571749,
+    5571750,
+    5571751,
+    5571752,
+    5571753,
+    5571754,
+    5571756,
+    5571757,
+    5571759,
+    5571760,
+    5571762,
+    5571764
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 4,
   "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 sha256:10c40b4016c15dd2de1dcf01c62f8c17b009a9a8677bd7ed240ac53785067b71
+oid sha256:7373f91dea4aa00e9461da8de72dc07e02a48a3efcbd86bba51cfc12d39af0ad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c101a2ecf159ac0131c6a7a72fce13978d9e60096c2f6bf085dacb87384a99
+oid sha256:d1651134325982f6302b947a402f038a26f6b808c9d67f7ee46dec2aa33fc00f
 size 4040701744