Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: lmind_hotpot_train8000_eval7405_v1_docidx_meta-llama_Llama-2-7b-hf_3e-5_lora2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# lmind_hotpot_train8000_eval7405_v1_docidx_meta-llama_Llama-2-7b-hf_3e-5_lora2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.0143
|
| 21 |
+
- Accuracy: 0.7798
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 3e-05
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- total_eval_batch_size: 8
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: constant
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 52 |
+
- num_epochs: 20.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 58 |
+
| 1.1149 | 1.0 | 839 | 1.3354 | 0.7522 |
|
| 59 |
+
| 1.0834 | 2.0 | 1678 | 1.3234 | 0.7536 |
|
| 60 |
+
| 1.0714 | 3.0 | 2517 | 1.2758 | 0.7554 |
|
| 61 |
+
| 1.0547 | 4.0 | 3357 | 1.2809 | 0.7570 |
|
| 62 |
+
| 1.0218 | 5.0 | 4196 | 1.2560 | 0.7587 |
|
| 63 |
+
| 0.9748 | 6.0 | 5035 | 1.2244 | 0.7605 |
|
| 64 |
+
| 0.9439 | 7.0 | 5874 | 1.1968 | 0.7621 |
|
| 65 |
+
| 0.9155 | 8.0 | 6714 | 1.1888 | 0.7634 |
|
| 66 |
+
| 0.8767 | 9.0 | 7553 | 1.1624 | 0.7651 |
|
| 67 |
+
| 0.848 | 10.0 | 8392 | 1.1410 | 0.7664 |
|
| 68 |
+
| 0.8227 | 11.0 | 9231 | 1.1288 | 0.7678 |
|
| 69 |
+
| 0.7874 | 12.0 | 10071 | 1.1165 | 0.7694 |
|
| 70 |
+
| 0.7469 | 13.0 | 10910 | 1.1008 | 0.7703 |
|
| 71 |
+
| 0.7256 | 14.0 | 11749 | 1.0892 | 0.7721 |
|
| 72 |
+
| 0.701 | 15.0 | 12588 | 1.0651 | 0.7732 |
|
| 73 |
+
| 0.6651 | 16.0 | 13428 | 1.0723 | 0.7746 |
|
| 74 |
+
| 0.6534 | 17.0 | 14267 | 1.0388 | 0.7759 |
|
| 75 |
+
| 0.6092 | 18.0 | 15106 | 1.0244 | 0.7774 |
|
| 76 |
+
| 0.5946 | 19.0 | 15945 | 1.0292 | 0.7784 |
|
| 77 |
+
| 0.5526 | 19.99 | 16780 | 1.0143 | 0.7798 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.34.0
|
| 83 |
+
- Pytorch 2.1.0+cu121
|
| 84 |
+
- Datasets 2.18.0
|
| 85 |
+
- Tokenizers 0.14.1
|