Run 4. Outer Step 62. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611413,
-    5611417,
-    5611422,
-    5611426,
-    5611430
+    5611435,
+    5611439,
+    5611443,
+    5611447,
+    5611452
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b32171ed5e6f2818722ec55bcbfbccdba511870658d6b9e34d8b90d57cdd0b2
+oid sha256:0d1e9de086fd0c8b073b234d0590cdb5fc3bd0c786d1272fb74bd65467a1ced8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0e1827ed7bec414b3aec8592cf5b460f7a79de18116c6a6a984ac6d5265256
+oid sha256:2a8d5a849f7869e0532e0819d7486c96ab6e7c26e52de24ca3dd2f1f2916478e
 size 4040701744