Run 4. Outer Step 61. Inner Step 38.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609857,
-    5609861,
-    5609865,
-    5609869,
-    5609874
+    5609879,
+    5609882,
+    5609887,
+    5609890,
+    5609894,
+    5609898,
+    5609902
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "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 sha256:5e26128f8d97720a7c7ec4c3e7dd5b9746d00756ee286952b321611ee752a86d
+oid sha256:660921ba4f08eeed430661eb0d15aa40ffad062a60717ee1a8def773ccf61cd6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c48e72cc12b33553d2179dae0bdc9b3d8473c85d4654bf92e75dccd303e52d
+oid sha256:3850b33c5fb46dc9db5a846216b94121b432100cead1b3f8cc0abcdf3f4dcc2c
 size 4040701744