Commit
•
5dd9801
1
Parent(s):
ff244d8
rishavranaut/llama3-8B_Fact_U
Browse files- README.md +85 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
model-index:
|
| 12 |
+
- name: llama3-8B_Fact_U
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# llama3-8B_Fact_U
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.1146
|
| 24 |
+
- Accuracy: 0.7953
|
| 25 |
+
- Precision: 0.8252
|
| 26 |
+
- Recall: 0.7692
|
| 27 |
+
- F1 score: 0.7963
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 0.0001
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 4
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 5
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 score |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
|
| 58 |
+
| 0.9272 | 0.2509 | 200 | 1.1877 | 0.5765 | 0.5589 | 0.8801 | 0.6837 |
|
| 59 |
+
| 0.7133 | 0.5019 | 400 | 0.7246 | 0.7 | 0.6912 | 0.7647 | 0.7261 |
|
| 60 |
+
| 0.6476 | 0.7528 | 600 | 0.6219 | 0.7565 | 0.7945 | 0.7172 | 0.7539 |
|
| 61 |
+
| 0.5766 | 1.0038 | 800 | 0.5714 | 0.76 | 0.85 | 0.6538 | 0.7391 |
|
| 62 |
+
| 0.4292 | 1.2547 | 1000 | 0.5870 | 0.7588 | 0.7474 | 0.8100 | 0.7774 |
|
| 63 |
+
| 0.4047 | 1.5056 | 1200 | 0.6078 | 0.7824 | 0.7694 | 0.8303 | 0.7987 |
|
| 64 |
+
| 0.4753 | 1.7566 | 1400 | 0.5654 | 0.7929 | 0.8575 | 0.7217 | 0.7838 |
|
| 65 |
+
| 0.3831 | 2.0075 | 1600 | 0.5672 | 0.8012 | 0.8289 | 0.7783 | 0.8028 |
|
| 66 |
+
| 0.2666 | 2.2585 | 1800 | 0.6054 | 0.8047 | 0.8416 | 0.7692 | 0.8038 |
|
| 67 |
+
| 0.3267 | 2.5094 | 2000 | 0.6620 | 0.7929 | 0.8182 | 0.7738 | 0.7953 |
|
| 68 |
+
| 0.2742 | 2.7604 | 2200 | 0.6985 | 0.7941 | 0.8579 | 0.7240 | 0.7853 |
|
| 69 |
+
| 0.3125 | 3.0113 | 2400 | 0.6373 | 0.7859 | 0.7955 | 0.7919 | 0.7937 |
|
| 70 |
+
| 0.1743 | 3.2622 | 2600 | 0.8362 | 0.8047 | 0.8730 | 0.7308 | 0.7956 |
|
| 71 |
+
| 0.1837 | 3.5132 | 2800 | 0.7889 | 0.7965 | 0.8440 | 0.7466 | 0.7923 |
|
| 72 |
+
| 0.2013 | 3.7641 | 3000 | 0.8958 | 0.7659 | 0.7425 | 0.8416 | 0.7890 |
|
| 73 |
+
| 0.1572 | 4.0151 | 3200 | 0.8662 | 0.8012 | 0.864 | 0.7330 | 0.7931 |
|
| 74 |
+
| 0.0993 | 4.2660 | 3400 | 0.8730 | 0.8024 | 0.8477 | 0.7557 | 0.7990 |
|
| 75 |
+
| 0.0704 | 4.5169 | 3600 | 1.0571 | 0.8012 | 0.8421 | 0.7602 | 0.7990 |
|
| 76 |
+
| 0.0598 | 4.7679 | 3800 | 1.1146 | 0.7953 | 0.8252 | 0.7692 | 0.7963 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- PEFT 0.11.1
|
| 82 |
+
- Transformers 4.44.2
|
| 83 |
+
- Pytorch 2.3.0+cu121
|
| 84 |
+
- Datasets 2.19.1
|
| 85 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 54593240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37baa7d3dde9a5bdc115484aa1aea1e646e232e47b3e7f5988ce80d9112cc5ba
|
| 3 |
size 54593240
|