Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: Qwen/Qwen1.5-4B
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: lmind_nq_train6000_eval6489_v1_docidx_v3_5e-4_lora2
|
| 10 |
+
results: []
|
| 11 |
+
library_name: peft
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# lmind_nq_train6000_eval6489_v1_docidx_v3_5e-4_lora2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 6.6284
|
| 22 |
+
- Accuracy: 0.38
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0005
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 8
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 8
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: constant
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 53 |
+
- num_epochs: 50.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 58 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
|
| 59 |
+
| 1.9636 | 0.9985 | 341 | 4.3673 | 0.4142 |
|
| 60 |
+
| 1.7006 | 2.0 | 683 | 4.5869 | 0.4334 |
|
| 61 |
+
| 1.3696 | 2.9985 | 1024 | 4.7205 | 0.4254 |
|
| 62 |
+
| 1.0297 | 4.0 | 1366 | 4.7833 | 0.4172 |
|
| 63 |
+
| 0.7991 | 4.9985 | 1707 | 4.9334 | 0.4169 |
|
| 64 |
+
| 0.5801 | 6.0 | 2049 | 5.1964 | 0.4134 |
|
| 65 |
+
| 0.4228 | 6.9985 | 2390 | 5.4040 | 0.4101 |
|
| 66 |
+
| 0.3691 | 8.0 | 2732 | 5.6553 | 0.4098 |
|
| 67 |
+
| 0.3052 | 8.9985 | 3073 | 5.5593 | 0.4122 |
|
| 68 |
+
| 0.2993 | 10.0 | 3415 | 5.6595 | 0.4115 |
|
| 69 |
+
| 0.2639 | 10.9985 | 3756 | 5.8112 | 0.4053 |
|
| 70 |
+
| 0.2447 | 12.0 | 4098 | 5.8116 | 0.4063 |
|
| 71 |
+
| 0.257 | 12.9985 | 4439 | 5.7970 | 0.4067 |
|
| 72 |
+
| 0.2346 | 14.0 | 4781 | 5.7984 | 0.4010 |
|
| 73 |
+
| 0.2477 | 14.9985 | 5122 | 5.9483 | 0.4007 |
|
| 74 |
+
| 0.2341 | 16.0 | 5464 | 6.0840 | 0.3997 |
|
| 75 |
+
| 0.2471 | 16.9985 | 5805 | 6.0255 | 0.3976 |
|
| 76 |
+
| 0.2303 | 18.0 | 6147 | 5.9475 | 0.4012 |
|
| 77 |
+
| 0.2165 | 18.9985 | 6488 | 6.3113 | 0.396 |
|
| 78 |
+
| 0.2293 | 20.0 | 6830 | 6.1628 | 0.3935 |
|
| 79 |
+
| 0.2193 | 20.9985 | 7171 | 6.3133 | 0.3883 |
|
| 80 |
+
| 0.2313 | 22.0 | 7513 | 6.1371 | 0.3915 |
|
| 81 |
+
| 0.217 | 22.9985 | 7854 | 6.0323 | 0.3932 |
|
| 82 |
+
| 0.205 | 24.0 | 8196 | 6.2038 | 0.3892 |
|
| 83 |
+
| 0.2208 | 24.9985 | 8537 | 6.0502 | 0.3894 |
|
| 84 |
+
| 0.2102 | 26.0 | 8879 | 6.1540 | 0.3836 |
|
| 85 |
+
| 0.2217 | 26.9985 | 9220 | 5.9979 | 0.388 |
|
| 86 |
+
| 0.209 | 28.0 | 9562 | 6.2838 | 0.3872 |
|
| 87 |
+
| 0.2206 | 28.9985 | 9903 | 6.1295 | 0.3867 |
|
| 88 |
+
| 0.2109 | 30.0 | 10245 | 6.2467 | 0.3889 |
|
| 89 |
+
| 0.1988 | 30.9985 | 10586 | 6.2880 | 0.3874 |
|
| 90 |
+
| 0.2167 | 32.0 | 10928 | 6.2385 | 0.386 |
|
| 91 |
+
| 0.2045 | 32.9985 | 11269 | 6.4127 | 0.3863 |
|
| 92 |
+
| 0.2146 | 34.0 | 11611 | 6.3402 | 0.3849 |
|
| 93 |
+
| 0.2049 | 34.9985 | 11952 | 6.3543 | 0.3872 |
|
| 94 |
+
| 0.1954 | 36.0 | 12294 | 6.4192 | 0.3846 |
|
| 95 |
+
| 0.2078 | 36.9985 | 12635 | 6.3592 | 0.3874 |
|
| 96 |
+
| 0.1977 | 38.0 | 12977 | 6.5489 | 0.3876 |
|
| 97 |
+
| 0.2094 | 38.9985 | 13318 | 6.3914 | 0.3903 |
|
| 98 |
+
| 0.2012 | 40.0 | 13660 | 6.4228 | 0.3889 |
|
| 99 |
+
| 0.2106 | 40.9985 | 14001 | 6.4559 | 0.3871 |
|
| 100 |
+
| 0.2015 | 42.0 | 14343 | 6.3730 | 0.3823 |
|
| 101 |
+
| 0.1921 | 42.9985 | 14684 | 6.3121 | 0.3826 |
|
| 102 |
+
| 0.2019 | 44.0 | 15026 | 6.3081 | 0.3827 |
|
| 103 |
+
| 0.1953 | 44.9985 | 15367 | 6.4581 | 0.3827 |
|
| 104 |
+
| 0.2077 | 46.0 | 15709 | 6.6189 | 0.3801 |
|
| 105 |
+
| 0.1997 | 46.9985 | 16050 | 6.4585 | 0.3835 |
|
| 106 |
+
| 0.1899 | 48.0 | 16392 | 6.6852 | 0.3792 |
|
| 107 |
+
| 0.1984 | 48.9985 | 16733 | 6.6309 | 0.3828 |
|
| 108 |
+
| 0.1895 | 49.9268 | 17050 | 6.6284 | 0.38 |
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
### Framework versions
|
| 112 |
+
|
| 113 |
+
- PEFT 0.5.0
|
| 114 |
+
- Transformers 4.41.1
|
| 115 |
+
- Pytorch 2.1.0+cu121
|
| 116 |
+
- Datasets 2.19.1
|
| 117 |
+
- Tokenizers 0.19.1
|