Outer Step 5. Inner Step 646. Batch Size 176

config.json

@@ -268,24 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5276890,
-    5276894,
-    5276899,
-    5276903,
-    5276907,
-    5276912,
-    5276916,
-    5276920,
-    5276925,
-    5276929,
-    5276935
+    5276967,
+    5276971,
+    5276976,
+    5276980,
+    5276984,
+    5276988,
+    5276992,
+    5276996,
+    5277000,
+    5277004,
+    5277010
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 636,
+  "inner_step": 646,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8562341b880915c3b317a51213336c0405e662cbf3b2798d17e5b9c73236938
+oid sha256:811289a16a56ecadde761b881392853763ca88e4b9030f881520b997c21f0df9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7eb824e6e9d888bc90e6934a45275d8b7937a4b48a426845c04e91a74749d8
+oid sha256:a87e2cb05d8f0135fff42ffd8464bdfeb1ce2f38abe63da6c746d015ff96aadc
 size 4040701744