Run 4. Outer Step 52. Inner Step 32.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575999,
-    5576003,
-    5576006,
-    5576009,
-    5576011,
-    5576014
+    5576016,
+    5576019,
+    5576023,
+    5576026,
+    5576028
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "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 sha256:2870fbc2f6b3912827a9ee6ba0a626f22fef10948666b25c9b6f14958020e0a3
+oid sha256:1cf927d321261638bf22c93749f49e67e060d719b602ba3d60f0f2258530464e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff29948f0855a782c24402e6a53943a83980cd26843cd1d8f7e5fd3ee68902cc
+oid sha256:51f2cfa7f99d6ca0d1d333db46cd5149fc9c96da3e6861e8070848b61a656bef
 size 4040701744