rishavranaut/LLAMA3_8b_LORA_FOR_CLASSIFICATION
Browse files
README.md
CHANGED
|
@@ -1,3 +1,119 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
model-index:
|
| 10 |
+
- name: LLAMA3_8b_LORA_FOR_CLASSIFICATION
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# LLAMA3_8b_LORA_FOR_CLASSIFICATION
|
| 18 |
+
|
| 19 |
+
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.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6062
|
| 22 |
+
- Balanced Accuracy: 0.86
|
| 23 |
+
- Accuracy: 0.86
|
| 24 |
+
- Micro F1: 0.86
|
| 25 |
+
- Macro F1: 0.8600
|
| 26 |
+
- Weighted F1: 0.8600
|
| 27 |
+
- Classification Report: precision recall f1-score support
|
| 28 |
+
|
| 29 |
+
0 0.86 0.85 0.86 200
|
| 30 |
+
1 0.86 0.86 0.86 200
|
| 31 |
+
|
| 32 |
+
accuracy 0.86 400
|
| 33 |
+
macro avg 0.86 0.86 0.86 400
|
| 34 |
+
weighted avg 0.86 0.86 0.86 400
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 0.0001
|
| 55 |
+
- train_batch_size: 8
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 5
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Accuracy | Balanced Accuracy | Classification Report | Validation Loss | Macro F1 | Micro F1 | Weighted F1 |
|
| 65 |
+
|:-------------:|:-----:|:----:|:--------:|:-----------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|:--------:|:--------:|:-----------:|
|
| 66 |
+
| 0.5306 | 1.0 | 732 | 0.8125 | 0.8125 | precision recall f1-score support
|
| 67 |
+
|
| 68 |
+
0 0.76 0.92 0.83 200
|
| 69 |
+
1 0.90 0.70 0.79 200
|
| 70 |
+
|
| 71 |
+
accuracy 0.81 400
|
| 72 |
+
macro avg 0.83 0.81 0.81 400
|
| 73 |
+
weighted avg 0.83 0.81 0.81 400
|
| 74 |
+
| 0.4840 | 0.8103 | 0.8125 | 0.8103 |
|
| 75 |
+
| 0.4284 | 2.0 | 1464 | 0.4444 | 0.815 | 0.815 | 0.815 | 0.8147 | 0.8147 | precision recall f1-score support
|
| 76 |
+
|
| 77 |
+
0 0.84 0.78 0.81 200
|
| 78 |
+
1 0.79 0.85 0.82 200
|
| 79 |
+
|
| 80 |
+
accuracy 0.81 400
|
| 81 |
+
macro avg 0.82 0.81 0.81 400
|
| 82 |
+
weighted avg 0.82 0.81 0.81 400
|
| 83 |
+
|
|
| 84 |
+
| 0.3809 | 3.0 | 2196 | 0.4513 | 0.8475 | 0.8475 | 0.8475 | 0.8470 | 0.8470 | precision recall f1-score support
|
| 85 |
+
|
| 86 |
+
0 0.81 0.91 0.86 200
|
| 87 |
+
1 0.89 0.79 0.84 200
|
| 88 |
+
|
| 89 |
+
accuracy 0.85 400
|
| 90 |
+
macro avg 0.85 0.85 0.85 400
|
| 91 |
+
weighted avg 0.85 0.85 0.85 400
|
| 92 |
+
|
|
| 93 |
+
| 0.2413 | 4.0 | 2928 | 0.5228 | 0.87 | 0.87 | 0.87 | 0.8700 | 0.8700 | precision recall f1-score support
|
| 94 |
+
|
| 95 |
+
0 0.87 0.86 0.87 200
|
| 96 |
+
1 0.87 0.88 0.87 200
|
| 97 |
+
|
| 98 |
+
accuracy 0.87 400
|
| 99 |
+
macro avg 0.87 0.87 0.87 400
|
| 100 |
+
weighted avg 0.87 0.87 0.87 400
|
| 101 |
+
|
|
| 102 |
+
| 0.1499 | 5.0 | 3660 | 0.6062 | 0.86 | 0.86 | 0.86 | 0.8600 | 0.8600 | precision recall f1-score support
|
| 103 |
+
|
| 104 |
+
0 0.86 0.85 0.86 200
|
| 105 |
+
1 0.86 0.86 0.86 200
|
| 106 |
+
|
| 107 |
+
accuracy 0.86 400
|
| 108 |
+
macro avg 0.86 0.86 0.86 400
|
| 109 |
+
weighted avg 0.86 0.86 0.86 400
|
| 110 |
+
|
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
### Framework versions
|
| 114 |
+
|
| 115 |
+
- PEFT 0.11.1
|
| 116 |
+
- Transformers 4.41.2
|
| 117 |
+
- Pytorch 2.3.0+cu121
|
| 118 |
+
- Datasets 2.19.1
|
| 119 |
+
- 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:e35bb30bf58f92f660383c5a379326a84a1d7c8d17d466cf066379d5d6edbb0a
|
| 3 |
size 54593240
|
runs/Jun26_20-23-12_iit-p/events.out.tfevents.1719413593.iit-p
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c02703c795ad4c3c03f7bab53a1cf040167dcb357d08a271a18e5e08b0e7205
|
| 3 |
+
size 14112
|