NibiruTwin
commited on
Commit
•
41b673b
1
Parent(s):
7d2e768
Update README.md
Browse files
README.md
CHANGED
@@ -81,6 +81,9 @@ num_train_epochs = 3,
|
|
81 |
O^O/ \_/ \ Batch size per device = 2 | Gradient Accumulation steps = 4
|
82 |
\ / Total batch size = 8 | Total steps = 36
|
83 |
"-____-" Number of trainable parameters = 125,173,760
|
|
|
|
|
|
|
84 |
[36/36 01:54, Epoch 2/3]
|
85 |
Step Training Loss rewards / chosen rewards / rejected rewards / accuracies rewards / margins logps / rejected logps / chosen logits / rejected logits / chosen
|
86 |
1 0.000100 3.348554 -6.467402 1.000000 9.815956 -169.229355 -175.684265 0.611595 0.875623
|
@@ -120,7 +123,6 @@ Step Training Loss rewards / chosen rewards / rejected rewards / accuracies rewa
|
|
120 |
35 0.000100 5.392914 -4.364581 1.000000 9.757494 -97.780762 -143.621002 0.270843 0.839165
|
121 |
36 0.000100 2.788383 -7.393952 1.000000 10.182335 -154.236618 -184.300690 0.392709 0.757870
|
122 |
TrainOutput(global_step=36, training_loss=0.00038064550871139445, metrics={'train_runtime': 118.2651, 'train_samples_per_second': 2.537, 'train_steps_per_second': 0.304, 'total_flos': 0.0, 'train_loss': 0.00038064550871139445, 'epoch': 2.88})
|
123 |
-
|
124 |
```
|
125 |
|
126 |
結果として大喜利については以下のような答えになっていました。
|
|
|
81 |
O^O/ \_/ \ Batch size per device = 2 | Gradient Accumulation steps = 4
|
82 |
\ / Total batch size = 8 | Total steps = 36
|
83 |
"-____-" Number of trainable parameters = 125,173,760
|
84 |
+
|
85 |
+
|
86 |
+
```python:
|
87 |
[36/36 01:54, Epoch 2/3]
|
88 |
Step Training Loss rewards / chosen rewards / rejected rewards / accuracies rewards / margins logps / rejected logps / chosen logits / rejected logits / chosen
|
89 |
1 0.000100 3.348554 -6.467402 1.000000 9.815956 -169.229355 -175.684265 0.611595 0.875623
|
|
|
123 |
35 0.000100 5.392914 -4.364581 1.000000 9.757494 -97.780762 -143.621002 0.270843 0.839165
|
124 |
36 0.000100 2.788383 -7.393952 1.000000 10.182335 -154.236618 -184.300690 0.392709 0.757870
|
125 |
TrainOutput(global_step=36, training_loss=0.00038064550871139445, metrics={'train_runtime': 118.2651, 'train_samples_per_second': 2.537, 'train_steps_per_second': 0.304, 'total_flos': 0.0, 'train_loss': 0.00038064550871139445, 'epoch': 2.88})
|
|
|
126 |
```
|
127 |
|
128 |
結果として大喜利については以下のような答えになっていました。
|