Run 4. Outer Step 33. Inner Step 30.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544760,
-    5544762,
-    5544764,
-    5544767,
-    5544770
+    5544772,
+    5544774,
+    5544777,
+    5544780,
+    5544781,
+    5544783,
+    5544786,
+    5544788,
+    5544790,
+    5544792,
+    5544793
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2669b350ad403514118c953d75fdca515ab622daedbcbc210d4ae87d27f3f448
+oid sha256:6cb23bb60f694d37d8faf9df7a66ec508be6e38e0114948d7b3aba341bba6823
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a93434e3c29f67c20a8a7aa557aa6d989172d72d2640b90a2cabdac9d70987
+oid sha256:cd0dcc577e86b3d9c6d77b09acd8dd99440511a597377469d1e95ead31812e74
 size 4040701744