update model card README.md

README.md

@@ -13,6 +13,13 @@ should probably proofread and complete it, then remove this comment. -->
 # DS-Chatbox-facebook-xglm-564M-V3
 
 This model is a fine-tuned version of [facebook/xglm-564M](https://huggingface.co/facebook/xglm-564M) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.5064
+- eval_runtime: 181.3835
+- eval_samples_per_second: 39.099
+- eval_steps_per_second: 4.89
+- epoch: 1.69
+- step: 3500
 
 ## Model description
 
@@ -31,14 +38,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0015
+- learning_rate: 7.500000000000001e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 1
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 5
 
 ### Framework versions