Outer Step 0. Inner Step 2. Batch Size 164

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "maher4488/minor8",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5129380,
-    5129392,
-    5129405,
-    5129413,
-    5129419
+    5129440,
+    5129449,
+    5129458,
+    5129466,
+    5129482
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6070,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf048843b09cdc2f951eea4cf46751cc4509c35be90d9ff8cc8cc8cbef82cf3
+oid sha256:12d4882fadd668d3a7c85905f80307d96a5205a261c36b4c4d71899951c025a5
 size 4040701744