Outer Step 4. Inner Step 63. Batch Size 0

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5149371,
-    5149376,
-    5149380,
-    5149385,
-    5149389,
-    5149394,
-    5149399,
-    5149404,
-    5149408,
-    5149413
+    5149447,
+    5149451,
+    5149456,
+    5149460,
+    5149464,
+    5149468,
+    5149472,
+    5149477,
+    5149481,
+    5149485
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 53,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5148895,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4ba5997764f9f5d39ad25152bd5defb22b29b13fd7bad5ec405c2dfb645b52
+oid sha256:bd836c5002386e9f29f6b0e9f336627589115b16421fc4cd95494276d740cc3b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a14b8b2a8218c72a29a49a7d51d51d6754bcf8cf1a733081dd771329760c896
+oid sha256:ae9a448616326e6cbc1c556b13a56a0701a3fad20ab75c2b6a457cbae8c03a64
 size 4040701744