Run 4. Outer Step 33. Inner Step 19.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544566,
-    5544569,
-    5544571,
-    5544573,
-    5544575,
-    5544577,
-    5544579,
-    5544581
+    5544583,
+    5544586,
+    5544589,
+    5544592,
+    5544593
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e7bae6df7f64b9a87d1e51aefdc8c51b8c036a045c763d82c1d2a0719c8184
+oid sha256:326afc57a84d6f230060dd73d2276f01714d1d68db456f6d7fa9ccd556668fae
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc9c2b4b3a862ad27f105f11196d03f38847ff1c35c3fa267031722580e39db
+oid sha256:d50c6d4d37c6da4aa904fbea20a20d59f0d8a469cf6c94f5f448e079befbb6ca
 size 4040701744