Update README.md
Browse files
README.md
CHANGED
|
@@ -8,26 +8,55 @@ tags:
|
|
| 8 |
model-index:
|
| 9 |
- name: llama2-7B-finetuned-chat-guanaco
|
| 10 |
results: []
|
|
|
|
| 11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
|
| 14 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
-
|
| 16 |
-
# llama2-7B-finetuned-chat-guanaco
|
| 17 |
|
| 18 |
-
This model
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
More information needed
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
|
@@ -44,10 +73,6 @@ The following hyperparameters were used during training:
|
|
| 44 |
- num_epochs: 3
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
-
### Training results
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- PEFT 0.12.0
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: llama2-7B-finetuned-chat-guanaco
|
| 10 |
results: []
|
| 11 |
+
license: mit
|
| 12 |
---
|
| 13 |
+
base_model: NousResearch/Llama-2-7b-chat-hf
|
| 14 |
+
library_name: peft
|
| 15 |
+
tags:
|
| 16 |
+
- trl
|
| 17 |
+
- sft
|
| 18 |
+
- generated_from_trainer
|
| 19 |
+
model-index:
|
| 20 |
+
- name: llama2-7B-finetuned-chat-guanaco
|
| 21 |
+
results: []
|
| 22 |
|
| 23 |
+
---
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
| 29 |
+
The __`llama2-7B-finetuned-chat-guanaco`__ model is a fine-tuned version of the [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) base model. This base model is a variant of LLaMA (Large Language Model Meta AI) designed for chat applications, optimized for conversational understanding and generation.
|
| 30 |
+
|
| 31 |
+
## Dataset used
|
| 32 |
+
|
| 33 |
+
[mlabonne/guanaco-llama2-1k](https://huggingface.co/mlabonne/guanaco-llama2-1k)
|
| 34 |
|
| 35 |
## Intended uses & limitations
|
| 36 |
|
| 37 |
More information needed
|
| 38 |
|
| 39 |
+
### Training results
|
| 40 |
|
| 41 |
+
The training loss over steps is as follows:
|
| 42 |
+
|
| 43 |
+
| Step | Training Loss |
|
| 44 |
+
|------|---------------|
|
| 45 |
+
| 25 | 1.823 |
|
| 46 |
+
| 50 | 2.056 |
|
| 47 |
+
| 75 | 1.829 |
|
| 48 |
+
| 100 | 1.744 |
|
| 49 |
+
| 125 | 1.717 |
|
| 50 |
+
| 150 | 1.412 |
|
| 51 |
+
| 175 | 1.506 |
|
| 52 |
+
| 200 | 1.446 |
|
| 53 |
+
| 225 | 1.499 |
|
| 54 |
+
| 250 | 1.432 |
|
| 55 |
+
| 275 | 1.281 |
|
| 56 |
+
| 300 | 1.341 |
|
| 57 |
+
| 325 | 1.345 |
|
| 58 |
+
| 350 | 1.391 |
|
| 59 |
+
| 375 | 1.388 |
|
| 60 |
|
| 61 |
## Training procedure
|
| 62 |
|
|
|
|
| 73 |
- num_epochs: 3
|
| 74 |
- mixed_precision_training: Native AMP
|
| 75 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
### Framework versions
|
| 77 |
|
| 78 |
- PEFT 0.12.0
|