End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2770
+- Loss: 1.1735
 
 ## Model description
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 18000
+- training_steps: 24000
 
 ### Training results
 
@@ -226,6 +226,66 @@ The following hyperparameters were used during training:
 | 1.2811        | 14.24 | 17800 | 1.2774          |
 | 1.2824        | 14.32 | 17900 | 1.2771          |
 | 1.2881        | 14.4  | 18000 | 1.2770          |
+| 1.2971        | 14.48 | 18100 | 1.2880          |
+| 1.2878        | 14.56 | 18200 | 1.2883          |
+| 1.3081        | 14.64 | 18300 | 1.2812          |
+| 1.2949        | 14.72 | 18400 | 1.2812          |
+| 1.3153        | 14.8  | 18500 | 1.2827          |
+| 1.3316        | 14.88 | 18600 | 1.2777          |
+| 1.3225        | 14.96 | 18700 | 1.2789          |
+| 1.3022        | 15.04 | 18800 | 1.2719          |
+| 1.2773        | 15.12 | 18900 | 1.2685          |
+| 1.2787        | 15.2  | 19000 | 1.2674          |
+| 1.2876        | 15.28 | 19100 | 1.2644          |
+| 1.2801        | 15.36 | 19200 | 1.2630          |
+| 1.3197        | 15.44 | 19300 | 1.2615          |
+| 1.2968        | 15.52 | 19400 | 1.2572          |
+| 1.2992        | 15.6  | 19500 | 1.2581          |
+| 1.2739        | 15.68 | 19600 | 1.2511          |
+| 1.2925        | 15.76 | 19700 | 1.2485          |
+| 1.2831        | 15.84 | 19800 | 1.2456          |
+| 1.3055        | 15.92 | 19900 | 1.2415          |
+| 1.2883        | 16.0  | 20000 | 1.2432          |
+| 1.2378        | 16.08 | 20100 | 1.2358          |
+| 1.2618        | 16.16 | 20200 | 1.2354          |
+| 1.2475        | 16.24 | 20300 | 1.2294          |
+| 1.2534        | 16.32 | 20400 | 1.2267          |
+| 1.2362        | 16.4  | 20500 | 1.2249          |
+| 1.2442        | 16.48 | 20600 | 1.2245          |
+| 1.2727        | 16.56 | 20700 | 1.2209          |
+| 1.2645        | 16.64 | 20800 | 1.2192          |
+| 1.2535        | 16.72 | 20900 | 1.2158          |
+| 1.2673        | 16.8  | 21000 | 1.2131          |
+| 1.2693        | 16.88 | 21100 | 1.2133          |
+| 1.2419        | 16.96 | 21200 | 1.2104          |
+| 1.2165        | 17.04 | 21300 | 1.2064          |
+| 1.2184        | 17.12 | 21400 | 1.2047          |
+| 1.2195        | 17.2  | 21500 | 1.2036          |
+| 1.2126        | 17.28 | 21600 | 1.2024          |
+| 1.2048        | 17.36 | 21700 | 1.1989          |
+| 1.2158        | 17.44 | 21800 | 1.1991          |
+| 1.2372        | 17.52 | 21900 | 1.1966          |
+| 1.2502        | 17.6  | 22000 | 1.1964          |
+| 1.23          | 17.68 | 22100 | 1.1924          |
+| 1.1967        | 17.76 | 22200 | 1.1913          |
+| 1.2021        | 17.84 | 22300 | 1.1896          |
+| 1.2323        | 17.92 | 22400 | 1.1904          |
+| 1.2276        | 18.0  | 22500 | 1.1872          |
+| 1.2072        | 18.08 | 22600 | 1.1851          |
+| 1.157         | 18.16 | 22700 | 1.1828          |
+| 1.1805        | 18.24 | 22800 | 1.1827          |
+| 1.1812        | 18.32 | 22900 | 1.1812          |
+| 1.1993        | 18.4  | 23000 | 1.1800          |
+| 1.1887        | 18.48 | 23100 | 1.1803          |
+| 1.194         | 18.56 | 23200 | 1.1779          |
+| 1.2097        | 18.64 | 23300 | 1.1777          |
+| 1.2049        | 18.72 | 23400 | 1.1769          |
+| 1.2002        | 18.8  | 23500 | 1.1758          |
+| 1.2178        | 18.88 | 23600 | 1.1755          |
+| 1.1969        | 18.96 | 23700 | 1.1745          |
+| 1.198         | 19.04 | 23800 | 1.1741          |
+| 1.1919        | 19.12 | 23900 | 1.1736          |
+| 1.149         | 19.2  | 24000 | 1.1735          |
 
 
 ### Framework versions