Outer Step 0. Inner Step 2. Batch Size 444

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "maher4488/minor2",
+  "_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": [
-    5129379,
-    5129387,
-    5129396,
-    5129407,
-    5129416
+    5129456,
+    5129463,
+    5129472,
+    5129487,
+    5129502
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6177,
+  "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:f30037166a7246b0b29f62ae816711b45024ba40b0d633c980529160fde62eaa
+oid sha256:6c1db0ef0b2d64303c137dee01af36f9582f231bcb010de13358d76884d9e97a
 size 4040701744