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: lmind_nq_train6000_eval6489_v1_doc_qa_v3_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_nq_train6000_eval6489_v1_doc_qa_v3_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: 2.0598
|
| 21 |
+
- Accuracy: 0.5423
|
| 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: 50.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 58 |
+
| 1.3948 | 1.0 | 529 | 1.3087 | 0.6132 |
|
| 59 |
+
| 1.3789 | 2.0 | 1058 | 1.2897 | 0.6146 |
|
| 60 |
+
| 1.3259 | 3.0 | 1587 | 1.2849 | 0.6179 |
|
| 61 |
+
| 1.2853 | 4.0 | 2116 | 1.3169 | 0.6159 |
|
| 62 |
+
| 1.2556 | 5.0 | 2645 | 1.3532 | 0.6132 |
|
| 63 |
+
| 1.1972 | 6.0 | 3174 | 1.4135 | 0.6126 |
|
| 64 |
+
| 1.1839 | 7.0 | 3703 | 1.5007 | 0.6081 |
|
| 65 |
+
| 1.1334 | 8.0 | 4232 | 1.5242 | 0.6074 |
|
| 66 |
+
| 1.0966 | 9.0 | 4761 | 1.6107 | 0.5803 |
|
| 67 |
+
| 1.0485 | 10.0 | 5290 | 1.6749 | 0.6049 |
|
| 68 |
+
| 1.021 | 11.0 | 5819 | 1.7324 | 0.6015 |
|
| 69 |
+
| 0.9918 | 12.0 | 6348 | 1.7632 | 0.6007 |
|
| 70 |
+
| 0.947 | 13.0 | 6877 | 1.8303 | 0.6011 |
|
| 71 |
+
| 0.9376 | 14.0 | 7406 | 1.8873 | 0.5991 |
|
| 72 |
+
| 0.898 | 15.0 | 7935 | 1.9688 | 0.5976 |
|
| 73 |
+
| 0.8559 | 16.0 | 8464 | 1.9724 | 0.5988 |
|
| 74 |
+
| 0.8348 | 17.0 | 8993 | 1.9815 | 0.5714 |
|
| 75 |
+
| 0.8106 | 18.0 | 9522 | 2.0386 | 0.598 |
|
| 76 |
+
| 0.7848 | 19.0 | 10051 | 2.0627 | 0.5964 |
|
| 77 |
+
| 0.745 | 20.0 | 10580 | 2.0825 | 0.5966 |
|
| 78 |
+
| 0.7208 | 21.0 | 11109 | 2.0959 | 0.5959 |
|
| 79 |
+
| 0.6842 | 22.0 | 11638 | 2.1534 | 0.5968 |
|
| 80 |
+
| 0.6661 | 23.0 | 12167 | 2.1792 | 0.5975 |
|
| 81 |
+
| 0.6193 | 24.0 | 12696 | 2.1530 | 0.5967 |
|
| 82 |
+
| 0.6064 | 25.0 | 13225 | 2.1720 | 0.5958 |
|
| 83 |
+
| 0.5776 | 26.0 | 13754 | 2.2162 | 0.5966 |
|
| 84 |
+
| 0.5492 | 27.0 | 14283 | 2.2382 | 0.5862 |
|
| 85 |
+
| 0.5256 | 28.0 | 14812 | 2.2273 | 0.5963 |
|
| 86 |
+
| 0.5128 | 29.0 | 15341 | 2.2448 | 0.5948 |
|
| 87 |
+
| 0.4846 | 30.0 | 15870 | 2.2697 | 0.5846 |
|
| 88 |
+
| 0.4623 | 31.0 | 16399 | 2.2425 | 0.5968 |
|
| 89 |
+
| 0.4468 | 32.0 | 16928 | 2.2654 | 0.5936 |
|
| 90 |
+
| 0.4714 | 33.0 | 17457 | 2.1317 | 0.5957 |
|
| 91 |
+
| 0.8308 | 34.0 | 17986 | 1.9392 | 0.5973 |
|
| 92 |
+
| 0.6478 | 35.0 | 18515 | 2.0346 | 0.5979 |
|
| 93 |
+
| 0.612 | 36.0 | 19044 | 2.0882 | 0.5978 |
|
| 94 |
+
| 0.5928 | 37.0 | 19573 | 2.1420 | 0.5970 |
|
| 95 |
+
| 0.5698 | 38.0 | 20102 | 2.1569 | 0.5966 |
|
| 96 |
+
| 0.5444 | 39.0 | 20631 | 2.1954 | 0.5956 |
|
| 97 |
+
| 0.5404 | 40.0 | 21160 | 2.1724 | 0.5942 |
|
| 98 |
+
| 0.5124 | 41.0 | 21689 | 2.2020 | 0.5939 |
|
| 99 |
+
| 0.5342 | 42.0 | 22218 | 2.1955 | 0.5938 |
|
| 100 |
+
| 0.5385 | 43.0 | 22747 | 2.1431 | 0.5946 |
|
| 101 |
+
| 0.5673 | 44.0 | 23276 | 2.1269 | 0.5948 |
|
| 102 |
+
| 0.7034 | 45.0 | 23805 | 2.0601 | 0.5917 |
|
| 103 |
+
| 1.0751 | 46.0 | 24334 | 1.8910 | 0.5861 |
|
| 104 |
+
| 1.9072 | 47.0 | 24863 | 2.1388 | 0.5518 |
|
| 105 |
+
| 5.2339 | 48.0 | 25392 | 4.4877 | 0.3825 |
|
| 106 |
+
| 2.573 | 49.0 | 25921 | 2.2255 | 0.5283 |
|
| 107 |
+
| 2.1439 | 50.0 | 26450 | 2.0598 | 0.5423 |
|
| 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
|