Hugging Face's logo

pjherron
/
llama-2-7B-Guanaco-QLoRA-AWQ

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
pjherron commited on
Commit
a6380cd
·
1 Parent(s): 318437d

training after 10 epochs

Browse files
Files changed (2) hide show
  1. README.md +22 -6
  2. runs/Nov09_04-32-01_209704c86495/events.out.tfevents.1699504339.209704c86495.97855.9 +2 -2
README.md CHANGED
@@ -5,6 +5,9 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - emotion
 
 
 
8
  model-index:
9
  - name: llama-2-7B-Guanaco-QLoRA-AWQ
10
  results: []
@@ -16,6 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
16
  # llama-2-7B-Guanaco-QLoRA-AWQ
17
 
18
  This model is a fine-tuned version of [TheBloke/llama-2-7B-Guanaco-QLoRA-AWQ](https://huggingface.co/TheBloke/llama-2-7B-Guanaco-QLoRA-AWQ) on the emotion dataset.
 
 
 
 
19
 
20
  ## Model description
21
 
@@ -35,19 +42,28 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 256
39
- - eval_batch_size: 256
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 1
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 1.0 | 63 | 1.6517 |
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  ### Framework versions
 
5
  - generated_from_trainer
6
  datasets:
7
  - emotion
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
  model-index:
12
  - name: llama-2-7B-Guanaco-QLoRA-AWQ
13
  results: []
 
19
  # llama-2-7B-Guanaco-QLoRA-AWQ
20
 
21
  This model is a fine-tuned version of [TheBloke/llama-2-7B-Guanaco-QLoRA-AWQ](https://huggingface.co/TheBloke/llama-2-7B-Guanaco-QLoRA-AWQ) on the emotion dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.7119
24
+ - Accuracy: 0.778
25
+ - F1: 0.7718
26
 
27
  ## Model description
28
 
 
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 2e-05
45
+ - train_batch_size: 8
46
+ - eval_batch_size: 8
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 10
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
57
+ | 1.5456 | 1.0 | 2000 | 1.5658 | 0.397 | 0.2952 |
58
+ | 1.3418 | 2.0 | 4000 | 1.4285 | 0.483 | 0.4464 |
59
+ | 1.1199 | 3.0 | 6000 | 1.3052 | 0.5285 | 0.4825 |
60
+ | 0.9157 | 4.0 | 8000 | 1.1448 | 0.5925 | 0.5616 |
61
+ | 0.695 | 5.0 | 10000 | 0.9214 | 0.6745 | 0.6638 |
62
+ | 0.5373 | 6.0 | 12000 | 0.8784 | 0.6925 | 0.6931 |
63
+ | 0.405 | 7.0 | 14000 | 0.7437 | 0.745 | 0.7362 |
64
+ | 0.2908 | 8.0 | 16000 | 0.7283 | 0.7625 | 0.7538 |
65
+ | 0.2407 | 9.0 | 18000 | 0.6977 | 0.7775 | 0.7745 |
66
+ | 0.1836 | 10.0 | 20000 | 0.7119 | 0.778 | 0.7718 |
67
 
68
 
69
  ### Framework versions
runs/Nov09_04-32-01_209704c86495/events.out.tfevents.1699504339.209704c86495.97855.9 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38111aa82374e2dfc76223e8b0557a4ef36df7c60351f53ee5f4bd2ffecbad9e
3
- size 14739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47f1c13bc05434ba5fe64a1f36a15cd0db90a6c500c7db998284c9ce866958a
3
+ size 15475