Run 4. Outer Step 57. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5600952,
-    5600960,
-    5600967,
-    5600974,
-    5600981
+    5600990,
+    5600997,
+    5601005,
+    5601012,
+    5601020
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "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 sha256:930ccd870cc2a7b6871b2fdec795905d7a52babb329114c24721fae38e28f8ec
+oid sha256:9499990968381110c87e945c00672b80cfbf8fda819a522dc98c41d202e6f258
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d47a785d2555e89519e469649bba396e7d25029ae15fca37f8522ac3433c08
+oid sha256:bc6f8fa2cc005eb9f0956c93b111063617b12344a6cd9e1f690e7710a69eef86
 size 4040701744