Outer Step 0. Inner Step 2. Batch Size 468

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "crypt0trading/c66-h2",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "SUCCESS",
@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5062961,
-    5062965,
-    5062969,
-    5062973,
-    5062977
+    5063043,
+    5063047,
+    5063050,
+    5063054,
+    5063058
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1633,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0ada79235b354fa53a276f1f862ab498798aada1ed5ea0dd38093c1d23839c
+oid sha256:27f4a666e1716cc5b7598b87b5026f01525ae1c93666eec159f3db46fbd0c586
 size 4040701744