Run 4. Outer Step 52. Inner Step 31.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575974,
-    5575978,
-    5575981,
-    5575984,
-    5575985,
-    5575986
+    5575990,
+    5575993,
+    5575995,
+    5575999,
+    5576002
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ca48ddda06123eca75a8f772b234e8005354d5d6a242822ac95e6dac01887c
+oid sha256:5dbb7113208a5b52a202ec8d71efd716a1ee5d912c57243be95b837f230d8044
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9256460bb3ad12fc0d7e6a5676917ecf7a2728eb7de3e725183f3925c5b5d4e4
+oid sha256:e0f25c5d27c6a75653dfd0c5321a9cea4cf3772ae5aec76b5fced23a622819f1
 size 4040701744