Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: squad_qa_title_v5_full_add3_meta-llama_Llama-2-7b-hf_1e-4_lora
|
| 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 |
+
# squad_qa_title_v5_full_add3_meta-llama_Llama-2-7b-hf_1e-4_lora
|
| 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: 2.0766
|
| 21 |
+
- Accuracy: 0.6869
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 8
|
| 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: 50.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 57 |
+
|:-------------:|:-----:|:----:|:--------:|:---------------:|
|
| 58 |
+
| 1.4665 | 1.0 | 158 | 0.7027 | 1.1937 |
|
| 59 |
+
| 0.8192 | 2.0 | 317 | 0.7082 | 1.1604 |
|
| 60 |
+
| 0.5795 | 2.99 | 475 | 0.7050 | 1.1993 |
|
| 61 |
+
| 0.3605 | 4.0 | 634 | 0.7037 | 1.2827 |
|
| 62 |
+
| 0.2894 | 5.0 | 793 | 0.7010 | 1.3732 |
|
| 63 |
+
| 0.2089 | 6.0 | 951 | 0.6985 | 1.4418 |
|
| 64 |
+
| 0.1866 | 7.0 | 1110 | 0.7002 | 1.4958 |
|
| 65 |
+
| 0.168 | 8.0 | 1269 | 0.6973 | 1.5733 |
|
| 66 |
+
| 0.1627 | 9.0 | 1427 | 0.6966 | 1.6454 |
|
| 67 |
+
| 0.1549 | 10.0 | 1586 | 0.6985 | 1.6570 |
|
| 68 |
+
| 0.1497 | 10.99 | 1744 | 0.6940 | 1.7429 |
|
| 69 |
+
| 0.1534 | 12.0 | 1903 | 0.6982 | 1.7459 |
|
| 70 |
+
| 0.1444 | 13.0 | 2062 | 0.6955 | 1.7857 |
|
| 71 |
+
| 0.148 | 14.0 | 2220 | 0.6954 | 1.7621 |
|
| 72 |
+
| 0.1462 | 15.0 | 2379 | 0.6957 | 1.7651 |
|
| 73 |
+
| 0.1464 | 16.0 | 2538 | 0.6962 | 1.7384 |
|
| 74 |
+
| 0.1405 | 17.0 | 2696 | 0.6935 | 1.8738 |
|
| 75 |
+
| 0.1394 | 18.0 | 2855 | 0.6941 | 1.8427 |
|
| 76 |
+
| 0.1445 | 18.99 | 3013 | 0.6937 | 1.7709 |
|
| 77 |
+
| 0.1389 | 20.0 | 3172 | 0.6934 | 1.8840 |
|
| 78 |
+
| 0.1413 | 21.0 | 3331 | 0.6948 | 1.8034 |
|
| 79 |
+
| 0.142 | 22.0 | 3489 | 0.6893 | 1.8046 |
|
| 80 |
+
| 0.1421 | 23.0 | 3648 | 0.6882 | 1.8369 |
|
| 81 |
+
| 0.144 | 24.0 | 3807 | 0.6858 | 1.8879 |
|
| 82 |
+
| 0.1348 | 25.0 | 3965 | 0.69 | 1.8530 |
|
| 83 |
+
| 0.138 | 26.0 | 4124 | 0.6905 | 1.8132 |
|
| 84 |
+
| 0.138 | 26.99 | 4282 | 0.6858 | 1.9304 |
|
| 85 |
+
| 0.137 | 28.0 | 4441 | 0.6877 | 1.9670 |
|
| 86 |
+
| 0.14 | 29.0 | 4600 | 0.6856 | 1.9993 |
|
| 87 |
+
| 0.1337 | 30.0 | 4758 | 0.6848 | 1.8712 |
|
| 88 |
+
| 0.1373 | 31.0 | 4917 | 0.6870 | 1.8732 |
|
| 89 |
+
| 0.134 | 32.0 | 5076 | 0.6862 | 1.9648 |
|
| 90 |
+
| 0.1363 | 33.0 | 5234 | 0.6872 | 1.9204 |
|
| 91 |
+
| 0.1365 | 34.0 | 5393 | 0.6854 | 1.9778 |
|
| 92 |
+
| 0.135 | 34.99 | 5551 | 0.6840 | 1.9516 |
|
| 93 |
+
| 0.1355 | 36.0 | 5710 | 0.6841 | 2.0177 |
|
| 94 |
+
| 0.1343 | 37.0 | 5869 | 0.6852 | 2.0255 |
|
| 95 |
+
| 0.1321 | 38.0 | 6027 | 0.6843 | 1.9995 |
|
| 96 |
+
| 0.1313 | 39.0 | 6162 | 1.9035 | 0.6838 |
|
| 97 |
+
| 0.1361 | 40.0 | 6321 | 1.9624 | 0.6850 |
|
| 98 |
+
| 0.1345 | 40.99 | 6479 | 1.9221 | 0.6861 |
|
| 99 |
+
| 0.1353 | 42.0 | 6638 | 2.0262 | 0.6841 |
|
| 100 |
+
| 0.1312 | 43.0 | 6797 | 1.9510 | 0.6859 |
|
| 101 |
+
| 0.1313 | 44.0 | 6955 | 2.0107 | 0.6845 |
|
| 102 |
+
| 0.13 | 45.0 | 7114 | 1.9279 | 0.6870 |
|
| 103 |
+
| 0.1311 | 46.0 | 7273 | 1.9542 | 0.6878 |
|
| 104 |
+
| 0.1326 | 47.0 | 7431 | 2.0657 | 0.6845 |
|
| 105 |
+
| 0.1292 | 48.0 | 7590 | 1.9569 | 0.6854 |
|
| 106 |
+
| 0.1315 | 48.99 | 7748 | 1.8985 | 0.6879 |
|
| 107 |
+
| 0.1341 | 49.95 | 7900 | 2.0766 | 0.6869 |
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
### Framework versions
|
| 111 |
+
|
| 112 |
+
- Transformers 4.34.0
|
| 113 |
+
- Pytorch 2.1.0+cu121
|
| 114 |
+
- Datasets 2.18.0
|
| 115 |
+
- Tokenizers 0.14.1
|