Run 4. Outer Step 61. Inner Step 37.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609835,
-    5609839,
-    5609843,
-    5609847,
-    5609852
+    5609857,
+    5609861,
+    5609865,
+    5609869,
+    5609874
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d38b01df34c3fbed903a7ba3f8dfa0a844addb46b12a11e0aa0e014920369a7
+oid sha256:5e26128f8d97720a7c7ec4c3e7dd5b9746d00756ee286952b321611ee752a86d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b816b19257b0e1b39491b8e843d800d97d195df909f8e313acce285de448bf
+oid sha256:e3c48e72cc12b33553d2179dae0bdc9b3d8473c85d4654bf92e75dccd303e52d
 size 4040701744