Run 4. Outer Step 48. Inner Step 109.

config.json

@@ -268,33 +268,32 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5570189,
-    5570190,
-    5570191,
-    5570192,
-    5570193,
-    5570193,
-    5570194,
-    5570195,
-    5570195,
-    5570196,
-    5570197,
-    5570199,
-    5570200,
-    5570201,
-    5570202,
-    5570203,
-    5570204,
-    5570205,
-    5570206,
-    5570207
+    5570208,
+    5570210,
+    5570211,
+    5570212,
+    5570213,
+    5570214,
+    5570215,
+    5570215,
+    5570216,
+    5570217,
+    5570218,
+    5570219,
+    5570220,
+    5570221,
+    5570223,
+    5570224,
+    5570225,
+    5570226,
+    5570227
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 107,
+  "inner_step": 109,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0b922330270ba85853c06ef117885195ac71b112112953326719dd812ee7a0
+oid sha256:4c5d23423cf2475415b7a2eafb2749943ec01ff246f0c0e858c5b1af1ef5a25b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8cbfbec2ca459d8d43a22cdcc57e8ff95f1a8765b75a6f1ce22d33c45b971c
+oid sha256:9e5f0f5d8ded158d781389284b7049ba3ac07b5a168b751c819194861ddf355d
 size 4040701744