Outer Step 0. Inner Step 136. Batch Size 208

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5131750,
-    5131755,
-    5131759,
-    5131764,
-    5131773,
-    5131781,
-    5131799,
-    5131807,
-    5131819,
-    5131827
+    5131855,
+    5131862,
+    5131874,
+    5131884,
+    5131894,
+    5131902,
+    5131909,
+    5131919,
+    5131927,
+    5131932
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 129,
+  "inner_step": 136,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb455e7acd8d8c601288778ba1f9d5ead5dc2b146fc5521d3648d3caa1a45b2
+oid sha256:072e2288dc9c9773fb287257ebdd334d3e9aa63c04bfd88dc464d3ba527709ba
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3156c7a0ef6c1e19e9ccfe27296ebc9caa44b85f35ea0251d4e9d5f0319749ed
+oid sha256:40894673063ecdae43d188f473155dc0b455da7bf9edaa84a637e59a3f1cd0d7
 size 4040701744