Commit
·
4f844e3
1
Parent(s):
a1d8a2a
End of training
Browse files
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: ttl-roleplay
|
| 8 |
results: []
|
|
@@ -33,12 +34,12 @@ More information needed
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 0.0002
|
| 36 |
-
- train_batch_size:
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: cosine
|
| 41 |
-
- training_steps:
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
| 44 |
### Training results
|
|
@@ -47,7 +48,8 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
-
-
|
| 51 |
-
-
|
|
|
|
| 52 |
- Datasets 2.15.0
|
| 53 |
-
- Tokenizers 0.15.0
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
base_model: TheBloke/zephyr-7B-beta-GPTQ
|
| 7 |
model-index:
|
| 8 |
- name: ttl-roleplay
|
| 9 |
results: []
|
|
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 0.0002
|
| 37 |
+
- train_batch_size: 32
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: cosine
|
| 42 |
+
- training_steps: 30
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
|
|
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
+
- PEFT 0.7.1
|
| 52 |
+
- Transformers 4.36.2
|
| 53 |
+
- Pytorch 2.1.0+cu118
|
| 54 |
- Datasets 2.15.0
|
| 55 |
+
- Tokenizers 0.15.0
|