Commit
•
e90731a
1
Parent(s):
60a7d5c
End of training
Browse files- README.md +91 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: llama3.1
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- bleu
|
| 10 |
+
- rouge
|
| 11 |
+
tags:
|
| 12 |
+
- trl
|
| 13 |
+
- sft
|
| 14 |
+
- generated_from_trainer
|
| 15 |
+
model-index:
|
| 16 |
+
- name: Llama3.1-8b-instruct-SFT-2024-09-18_LoRAs
|
| 17 |
+
results: []
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 21 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 22 |
+
|
| 23 |
+
# Llama3.1-8b-instruct-SFT-2024-09-18_LoRAs
|
| 24 |
+
|
| 25 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
|
| 26 |
+
It achieves the following results on the evaluation set:
|
| 27 |
+
- Loss: 0.9931
|
| 28 |
+
- Accuracy: 0.0009
|
| 29 |
+
- Bleu: 0.5303
|
| 30 |
+
- Rouge1: 0.7979
|
| 31 |
+
- Rouge2: 0.5322
|
| 32 |
+
- Rougel: 0.6881
|
| 33 |
+
- Rougelsum: 0.7836
|
| 34 |
+
- Perplexity: 2.6995
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 1e-05
|
| 54 |
+
- train_batch_size: 6
|
| 55 |
+
- eval_batch_size: 1
|
| 56 |
+
- seed: 42
|
| 57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
+
- lr_scheduler_type: constant
|
| 59 |
+
- num_epochs: 1.5
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Bleu | Rouge1 | Rouge2 | Rougel | Rougelsum | Perplexity |
|
| 64 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:---------:|:----------:|
|
| 65 |
+
| 1.8865 | 0.0812 | 100 | 1.4597 | 0.0010 | 0.4381 | 0.7484 | 0.4472 | 0.6115 | 0.7309 | 4.3047 |
|
| 66 |
+
| 1.556 | 0.1625 | 200 | 1.3056 | 0.0007 | 0.4613 | 0.7654 | 0.4686 | 0.6322 | 0.7469 | 3.6898 |
|
| 67 |
+
| 1.4258 | 0.2437 | 300 | 1.2155 | 0.0007 | 0.4815 | 0.7745 | 0.4848 | 0.6475 | 0.7567 | 3.3720 |
|
| 68 |
+
| 1.3455 | 0.3249 | 400 | 1.1721 | 0.0007 | 0.4877 | 0.7756 | 0.4906 | 0.6551 | 0.7588 | 3.2287 |
|
| 69 |
+
| 1.2937 | 0.4062 | 500 | 1.1408 | 0.0009 | 0.4944 | 0.7808 | 0.4958 | 0.6591 | 0.7640 | 3.1291 |
|
| 70 |
+
| 1.2661 | 0.4874 | 600 | 1.1149 | 0.0008 | 0.5032 | 0.7854 | 0.5060 | 0.6659 | 0.7694 | 3.0491 |
|
| 71 |
+
| 1.2571 | 0.5686 | 700 | 1.0901 | 0.0009 | 0.5081 | 0.7897 | 0.5105 | 0.6707 | 0.7749 | 2.9745 |
|
| 72 |
+
| 1.2529 | 0.6499 | 800 | 1.0758 | 0.0009 | 0.5130 | 0.7888 | 0.5151 | 0.6739 | 0.7720 | 2.9322 |
|
| 73 |
+
| 1.2122 | 0.7311 | 900 | 1.0639 | 0.0010 | 0.5133 | 0.7895 | 0.5158 | 0.6737 | 0.7737 | 2.8974 |
|
| 74 |
+
| 1.2081 | 0.8123 | 1000 | 1.0521 | 0.0009 | 0.5144 | 0.7902 | 0.5148 | 0.6755 | 0.7743 | 2.8636 |
|
| 75 |
+
| 1.1804 | 0.8936 | 1100 | 1.0411 | 0.0009 | 0.5175 | 0.7920 | 0.5192 | 0.6789 | 0.7770 | 2.8321 |
|
| 76 |
+
| 1.1616 | 0.9748 | 1200 | 1.0311 | 0.0009 | 0.5209 | 0.7924 | 0.5205 | 0.6794 | 0.7764 | 2.8041 |
|
| 77 |
+
| 1.1607 | 1.0561 | 1300 | 1.0244 | 0.0010 | 0.5215 | 0.7935 | 0.5243 | 0.6812 | 0.7787 | 2.7855 |
|
| 78 |
+
| 1.1554 | 1.1373 | 1400 | 1.0168 | 0.0010 | 0.5241 | 0.7953 | 0.5258 | 0.6830 | 0.7800 | 2.7642 |
|
| 79 |
+
| 1.153 | 1.2185 | 1500 | 1.0103 | 0.0009 | 0.5263 | 0.7957 | 0.5263 | 0.6841 | 0.7812 | 2.7464 |
|
| 80 |
+
| 1.1488 | 1.2998 | 1600 | 1.0032 | 0.0009 | 0.5250 | 0.7969 | 0.5284 | 0.6842 | 0.7815 | 2.7268 |
|
| 81 |
+
| 1.1488 | 1.3810 | 1700 | 0.9979 | 0.0010 | 0.5280 | 0.7979 | 0.5281 | 0.6864 | 0.7819 | 2.7126 |
|
| 82 |
+
| 1.1529 | 1.4622 | 1800 | 0.9931 | 0.0009 | 0.5303 | 0.7979 | 0.5322 | 0.6881 | 0.7836 | 2.6995 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- PEFT 0.12.0
|
| 88 |
+
- Transformers 4.44.2
|
| 89 |
+
- Pytorch 2.0.1+cu118
|
| 90 |
+
- Datasets 3.0.0
|
| 91 |
+
- 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 2806378968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0237b5ba016d4c03cafe7aae828b28e24f2b9bc90e11472e377154947868835
|
| 3 |
size 2806378968
|