Update README.md
Browse files
README.md
CHANGED
|
@@ -2,9 +2,7 @@
|
|
| 2 |
license: other
|
| 3 |
base_model: NousResearch/Llama-2-7b-chat-hf
|
| 4 |
tags:
|
| 5 |
-
-
|
| 6 |
-
- lora
|
| 7 |
-
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: 2023-11-29-06-20-56
|
| 10 |
results: []
|
|
@@ -29,20 +27,6 @@ More information needed
|
|
| 29 |
|
| 30 |
More information needed
|
| 31 |
|
| 32 |
-
## Training procedure
|
| 33 |
-
|
| 34 |
-
### Training hyperparameters
|
| 35 |
-
|
| 36 |
-
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 5e-05
|
| 38 |
-
- train_batch_size: 4
|
| 39 |
-
- eval_batch_size: 8
|
| 40 |
-
- seed: 42
|
| 41 |
-
- gradient_accumulation_steps: 4
|
| 42 |
-
- total_train_batch_size: 16
|
| 43 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
-
- lr_scheduler_type: cosine
|
| 45 |
-
- num_epochs: 3.0
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
@@ -53,4 +37,4 @@ The following hyperparameters were used during training:
|
|
| 53 |
- Transformers 4.34.1
|
| 54 |
- Pytorch 2.1.0+cu118
|
| 55 |
- Datasets 2.14.7
|
| 56 |
-
- Tokenizers 0.14.1
|
|
|
|
| 2 |
license: other
|
| 3 |
base_model: NousResearch/Llama-2-7b-chat-hf
|
| 4 |
tags:
|
| 5 |
+
- biology
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: 2023-11-29-06-20-56
|
| 8 |
results: []
|
|
|
|
| 27 |
|
| 28 |
More information needed
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
### Training results
|
| 32 |
|
|
|
|
| 37 |
- Transformers 4.34.1
|
| 38 |
- Pytorch 2.1.0+cu118
|
| 39 |
- Datasets 2.14.7
|
| 40 |
+
- Tokenizers 0.14.1
|