Run 4. Outer Step 62. Inner Step 35.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611619,
-    5611623,
-    5611628,
-    5611632,
-    5611637
+    5611641,
+    5611646,
+    5611650,
+    5611655,
+    5611658
   ],
   "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": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d256ca6ac5af03386c648d81cb93d4d290675ccc4c52fbb09b6d5ddd92863434
+oid sha256:b9942c54605dc702ca930118c819cb81b5c7e67cf51e35200f14bec098e9892c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f8a1e423edd99d500ff5a65287156173080a70c87dd06e7c3195b1348cc917
+oid sha256:ec5c355db621ac68fb50456e174437a55499d2645b22782719b94e0264540b84
 size 4040701744