Run 4. Outer Step 53. Inner Step 80.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588943,
-    5588947,
-    5588951,
-    5588955,
-    5588959
+    5588963,
+    5588968,
+    5588972,
+    5588976,
+    5588980,
+    5588985
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de39630fc6abfa021d8e600d3f0321840ffb26b8179c1aea6f5b7691775a11b
+oid sha256:2b3a3aff58ae7698e94595808bc0b7ba8418ea3a44f2365a5e43980a53e52373
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235c1143bf1feb57dd7e4b9c8523d45d260107d63c804d68a8e72e9cf4b979cc
+oid sha256:808f8b71534157a86ccf4764f44a445d814c6a569c202f5a2e3a4587f68bbc6a
 size 4040701744