Model save
Browse files- README.md +83 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3.1
|
| 4 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- dpo
|
| 8 |
+
- llama-factory
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: Llama-3.1-8B-Instruct-dpo-mistral-1000
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# Llama-3.1-8B-Instruct-dpo-mistral-1000
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4934
|
| 23 |
+
- Rewards/chosen: 0.8943
|
| 24 |
+
- Rewards/rejected: -0.7017
|
| 25 |
+
- Rewards/accuracies: 0.75
|
| 26 |
+
- Rewards/margins: 1.5960
|
| 27 |
+
- Logps/chosen: -14.2081
|
| 28 |
+
- Logps/rejected: -32.2463
|
| 29 |
+
- Logits/chosen: -0.0873
|
| 30 |
+
- Logits/rejected: -0.1548
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 5e-06
|
| 50 |
+
- train_batch_size: 2
|
| 51 |
+
- eval_batch_size: 2
|
| 52 |
+
- seed: 42
|
| 53 |
+
- gradient_accumulation_steps: 8
|
| 54 |
+
- total_train_batch_size: 16
|
| 55 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 56 |
+
- lr_scheduler_type: cosine
|
| 57 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 58 |
+
- num_epochs: 10.0
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/chosen | Logps/rejected | Logits/chosen | Logits/rejected |
|
| 63 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:------------:|:--------------:|:-------------:|:---------------:|
|
| 64 |
+
| 0.6891 | 0.8909 | 50 | 0.6833 | 0.0487 | 0.0276 | 0.6200 | 0.0211 | -22.6647 | -24.9535 | -0.3207 | -0.3690 |
|
| 65 |
+
| 0.5716 | 1.7817 | 100 | 0.5618 | 0.6081 | 0.1913 | 0.7000 | 0.4168 | -17.0706 | -23.3165 | -0.2934 | -0.3456 |
|
| 66 |
+
| 0.4581 | 2.6726 | 150 | 0.4761 | 0.9362 | -0.0437 | 0.7600 | 0.9799 | -13.7892 | -25.6666 | -0.2093 | -0.2739 |
|
| 67 |
+
| 0.4032 | 3.5635 | 200 | 0.4709 | 0.9603 | -0.2844 | 0.8100 | 1.2447 | -13.5486 | -28.0732 | -0.1631 | -0.2306 |
|
| 68 |
+
| 0.3836 | 4.4543 | 250 | 0.4675 | 0.9903 | -0.3997 | 0.7900 | 1.3900 | -13.2488 | -29.2269 | -0.1396 | -0.2080 |
|
| 69 |
+
| 0.3588 | 5.3452 | 300 | 0.4752 | 0.9745 | -0.4525 | 0.7700 | 1.4270 | -13.4066 | -29.7545 | -0.1255 | -0.1931 |
|
| 70 |
+
| 0.2861 | 6.2361 | 350 | 0.4812 | 0.9392 | -0.5503 | 0.7700 | 1.4895 | -13.7591 | -30.7320 | -0.1102 | -0.1785 |
|
| 71 |
+
| 0.3662 | 7.1269 | 400 | 0.4868 | 0.9165 | -0.6356 | 0.7700 | 1.5522 | -13.9862 | -31.5858 | -0.0990 | -0.1679 |
|
| 72 |
+
| 0.2822 | 8.0178 | 450 | 0.4927 | 0.9099 | -0.6512 | 0.7600 | 1.5612 | -14.0519 | -31.7416 | -0.0936 | -0.1622 |
|
| 73 |
+
| 0.2416 | 8.9087 | 500 | 0.4979 | 0.8912 | -0.6958 | 0.7600 | 1.5870 | -14.2398 | -32.1878 | -0.0898 | -0.1585 |
|
| 74 |
+
| 0.3096 | 9.7996 | 550 | 0.4934 | 0.8943 | -0.7017 | 0.75 | 1.5960 | -14.2081 | -32.2463 | -0.0873 | -0.1548 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- PEFT 0.12.0
|
| 80 |
+
- Transformers 4.46.1
|
| 81 |
+
- Pytorch 2.5.1+cu124
|
| 82 |
+
- Datasets 3.1.0
|
| 83 |
+
- Tokenizers 0.20.3
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42deb574e845f8684c09bbefceefd19768e431e4053ca1d18e3f2c8bac98a403
|
| 3 |
size 83945296
|