Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,56 @@ pipeline_tag: text-generation
|
|
| 15 |
|
| 16 |
### Open-Hermes-2.0 (Only first 1500 examples): **[ 1530/125193 4:46:45 < 386:48:08, 0.09 it/s, Epoch 0.01/1]**
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
```py
|
| 20 |
from trl import SFTTrainer
|
|
|
|
| 15 |
|
| 16 |
### Open-Hermes-2.0 (Only first 1500 examples): **[ 1530/125193 4:46:45 < 386:48:08, 0.09 it/s, Epoch 0.01/1]**
|
| 17 |
|
| 18 |
+
```
|
| 19 |
+
1483 5.986700
|
| 20 |
+
1484 5.764100
|
| 21 |
+
1485 5.887200
|
| 22 |
+
1486 5.445200
|
| 23 |
+
1487 6.086300
|
| 24 |
+
1488 5.718300
|
| 25 |
+
1489 5.670300
|
| 26 |
+
1490 5.440900
|
| 27 |
+
1491 4.945900
|
| 28 |
+
1492 6.154700
|
| 29 |
+
1493 5.624800
|
| 30 |
+
1494 6.868100
|
| 31 |
+
1495 5.627100
|
| 32 |
+
1496 5.192700
|
| 33 |
+
1497 5.826800
|
| 34 |
+
1498 5.512200
|
| 35 |
+
1499 5.869900
|
| 36 |
+
1500 5.852300
|
| 37 |
+
1501 5.574800
|
| 38 |
+
1502 5.299200
|
| 39 |
+
1503 5.631200
|
| 40 |
+
1504 5.535600
|
| 41 |
+
1505 5.626000
|
| 42 |
+
1506 5.093300
|
| 43 |
+
1507 5.278000
|
| 44 |
+
1508 5.585400
|
| 45 |
+
1509 5.318600
|
| 46 |
+
1510 5.319200
|
| 47 |
+
1511 5.513900
|
| 48 |
+
1512 5.375400
|
| 49 |
+
1513 5.460600
|
| 50 |
+
1514 5.045300
|
| 51 |
+
1515 6.013600
|
| 52 |
+
1516 5.812300
|
| 53 |
+
1517 5.707400
|
| 54 |
+
1518 5.109800
|
| 55 |
+
1519 5.212900
|
| 56 |
+
1520 5.317200
|
| 57 |
+
1521 5.935400
|
| 58 |
+
1522 5.733900
|
| 59 |
+
1523 5.866000
|
| 60 |
+
1524 5.675400
|
| 61 |
+
1525 5.580800
|
| 62 |
+
1526 4.996900
|
| 63 |
+
1527 5.666700
|
| 64 |
+
1528 4.979900
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
### Hyperparameters
|
| 68 |
|
| 69 |
```py
|
| 70 |
from trl import SFTTrainer
|