Update README.md

README.md

@@ -420,20 +420,20 @@ unfrozen_parameters:
   - model.layers.12.block_sparse_moe.experts.7.w3
   - model.layers.13.block_sparse_moe.experts.7.w3
   - model.layers.14.block_sparse_moe.experts.7.w3
-  # - model.layers.0.block_sparse_moe.gate
-  # - model.layers.1.block_sparse_moe.gate
-  # - model.layers.2.block_sparse_moe.gate
-  # - model.layers.3.block_sparse_moe.gate
-  # - model.layers.4.block_sparse_moe.gate
-  # - model.layers.5.block_sparse_moe.gate
-  # - model.layers.6.block_sparse_moe.gate
-  # - model.layers.7.block_sparse_moe.gate
-  # - model.layers.8.block_sparse_moe.gate
-  # - model.layers.9.block_sparse_moe.gate
-  # - model.layers.10.block_sparse_moe.gate
-  # - model.layers.11.block_sparse_moe.gate
-  # - model.layers.12.block_sparse_moe.gate
-  # - model.layers.13.block_sparse_moe.gate
+  - model.layers.0.block_sparse_moe.gate
+  - model.layers.1.block_sparse_moe.gate
+  - model.layers.2.block_sparse_moe.gate
+  - model.layers.3.block_sparse_moe.gate
+  - model.layers.4.block_sparse_moe.gate
+  - model.layers.5.block_sparse_moe.gate
+  - model.layers.6.block_sparse_moe.gate
+  - model.layers.7.block_sparse_moe.gate
+  - model.layers.8.block_sparse_moe.gate
+  - model.layers.9.block_sparse_moe.gate
+  - model.layers.10.block_sparse_moe.gate
+  - model.layers.11.block_sparse_moe.gate
+  - model.layers.12.block_sparse_moe.gate
+  - model.layers.13.block_sparse_moe.gate
   
 model_config:
   output_router_logits: true
@@ -541,43 +541,6 @@ tokens:
 
 </details><br>
 
-# out
-
-This model is a fine-tuned version of [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5217
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 2.7e-05
-- train_batch_size: 4
-- eval_batch_size: 4
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 256
-- total_eval_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 2
-- num_epochs: 3
-
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |