qwen-final-jeopardy
Browse files
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen-14B
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- jeopardy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: final_jeopardy
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# final_jeopardy
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [Qwen/Qwen-14B](https://huggingface.co/Qwen/Qwen-14B) on the jeopardy dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.3619
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 0.01
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 3.0584 | 0.02 | 100 | 2.6536 |
|
| 54 |
+
| 2.6474 | 0.04 | 200 | 2.5669 |
|
| 55 |
+
| 2.5729 | 0.06 | 300 | 2.5225 |
|
| 56 |
+
| 2.5364 | 0.08 | 400 | 2.5054 |
|
| 57 |
+
| 2.4918 | 0.1 | 500 | 2.4876 |
|
| 58 |
+
| 2.502 | 0.12 | 600 | 2.4734 |
|
| 59 |
+
| 2.4993 | 0.14 | 700 | 2.4651 |
|
| 60 |
+
| 2.4982 | 0.16 | 800 | 2.4514 |
|
| 61 |
+
| 2.4676 | 0.18 | 900 | 2.4419 |
|
| 62 |
+
| 2.4414 | 0.2 | 1000 | 2.4396 |
|
| 63 |
+
| 2.4656 | 0.22 | 1100 | 2.4292 |
|
| 64 |
+
| 2.4795 | 0.24 | 1200 | 2.4250 |
|
| 65 |
+
| 2.4341 | 0.26 | 1300 | 2.4228 |
|
| 66 |
+
| 2.4276 | 0.28 | 1400 | 2.4157 |
|
| 67 |
+
| 2.4297 | 0.3 | 1500 | 2.4105 |
|
| 68 |
+
| 2.4617 | 0.32 | 1600 | 2.4084 |
|
| 69 |
+
| 2.4431 | 0.34 | 1700 | 2.4016 |
|
| 70 |
+
| 2.4037 | 0.36 | 1800 | 2.4002 |
|
| 71 |
+
| 2.4289 | 0.38 | 1900 | 2.3984 |
|
| 72 |
+
| 2.4351 | 0.4 | 2000 | 2.3922 |
|
| 73 |
+
| 2.3931 | 0.42 | 2100 | 2.3920 |
|
| 74 |
+
| 2.4253 | 0.44 | 2200 | 2.3892 |
|
| 75 |
+
| 2.4507 | 0.46 | 2300 | 2.3856 |
|
| 76 |
+
| 2.4063 | 0.48 | 2400 | 2.3846 |
|
| 77 |
+
| 2.4253 | 0.5 | 2500 | 2.3825 |
|
| 78 |
+
| 2.3948 | 0.52 | 2600 | 2.3778 |
|
| 79 |
+
| 2.3839 | 0.54 | 2700 | 2.3781 |
|
| 80 |
+
| 2.4304 | 0.56 | 2800 | 2.3799 |
|
| 81 |
+
| 2.4458 | 0.58 | 2900 | 2.3723 |
|
| 82 |
+
| 2.4051 | 0.6 | 3000 | 2.3733 |
|
| 83 |
+
| 2.3984 | 0.62 | 3100 | 2.3713 |
|
| 84 |
+
| 2.3886 | 0.64 | 3200 | 2.3702 |
|
| 85 |
+
| 2.3625 | 0.66 | 3300 | 2.3717 |
|
| 86 |
+
| 2.3745 | 0.68 | 3400 | 2.3676 |
|
| 87 |
+
| 2.4168 | 0.7 | 3500 | 2.3665 |
|
| 88 |
+
| 2.3761 | 0.72 | 3600 | 2.3669 |
|
| 89 |
+
| 2.379 | 0.74 | 3700 | 2.3662 |
|
| 90 |
+
| 2.3801 | 0.76 | 3800 | 2.3642 |
|
| 91 |
+
| 2.3817 | 0.78 | 3900 | 2.3640 |
|
| 92 |
+
| 2.4002 | 0.8 | 4000 | 2.3645 |
|
| 93 |
+
| 2.3989 | 0.82 | 4100 | 2.3635 |
|
| 94 |
+
| 2.3916 | 0.84 | 4200 | 2.3629 |
|
| 95 |
+
| 2.4045 | 0.86 | 4300 | 2.3624 |
|
| 96 |
+
| 2.3919 | 0.88 | 4400 | 2.3626 |
|
| 97 |
+
| 2.3943 | 0.9 | 4500 | 2.3626 |
|
| 98 |
+
| 2.3896 | 0.92 | 4600 | 2.3616 |
|
| 99 |
+
| 2.3518 | 0.94 | 4700 | 2.3621 |
|
| 100 |
+
| 2.41 | 0.96 | 4800 | 2.3616 |
|
| 101 |
+
| 2.3782 | 0.98 | 4900 | 2.3621 |
|
| 102 |
+
| 2.3589 | 1.0 | 5000 | 2.3619 |
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
### Framework versions
|
| 106 |
+
|
| 107 |
+
- Transformers 4.32.0
|
| 108 |
+
- Pytorch 2.1.0
|
| 109 |
+
- Datasets 2.14.7
|
| 110 |
+
- Tokenizers 0.13.3
|