Na0s
/

Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Na0s commited on Aug 7

Commit

0acba52

•

1 Parent(s): dd502ac

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -22,6 +22,7 @@ base_model: Na0s/Llama-3.1-8b-Pruned-4-Layers
         batch_size=2,
         steps=10000, gradient_accumulation_steps = 4,
         warmup_steps = 5,
         learning_rate = 2e-4,
         fp16 = not is_bfloat16_supported(),
         bf16 = is_bfloat16_supported(),
@@ -29,7 +30,7 @@ base_model: Na0s/Llama-3.1-8b-Pruned-4-Layers
         optim = "adamw_8bit",
         weight_decay = 0.01,
         lr_scheduler_type = "linear",
-        seed = 3407,
 ### Training Data

         batch_size=2,
         steps=10000, gradient_accumulation_steps = 4,
         warmup_steps = 5,
+        max_steps = 10000
         learning_rate = 2e-4,
         fp16 = not is_bfloat16_supported(),
         bf16 = is_bfloat16_supported(),
         optim = "adamw_8bit",
         weight_decay = 0.01,
         lr_scheduler_type = "linear",
+        seed = 3407
 ### Training Data