mwz commited on
Commit
1566d52
1 Parent(s): 8f07e4f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -79,6 +79,14 @@ The following hyperparameters were used during training:
79
  | 0.2633 | 2.0 | 5000 | 0.4007 |
80
  | 0.1205 | 3.0 | 7500 | 0.4703 |
81
 
 
 
 
 
 
 
 
 
82
 
83
  ### Framework versions
84
 
 
79
  | 0.2633 | 2.0 | 5000 | 0.4007 |
80
  | 0.1205 | 3.0 | 7500 | 0.4703 |
81
 
82
+ ## Evaluation Results
83
+ The model was evaluated on an undisclosed dataset using a language modeling task. The evaluation results after 3 epochs of fine-tuning are as follows:
84
+
85
+ - Evaluation Loss: 0.3954
86
+ - Evaluation Runtime: 51.60 seconds
87
+ - Average Samples per Second: 96.89
88
+ - Average Steps per Second: 6.06
89
+ - Epoch: 3.0
90
 
91
  ### Framework versions
92