Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_3e-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_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_3e-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: 0.4756
|
| 22 |
+
- Accuracy: 0.7764
|
| 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: 0.0003
|
| 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: 20.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 58 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
|
| 59 |
+
| 1.5356 | 0.9998 | 1089 | 1.3711 | 0.6864 |
|
| 60 |
+
| 1.3102 | 1.9995 | 2178 | 1.1753 | 0.7020 |
|
| 61 |
+
| 1.0549 | 2.9993 | 3267 | 1.0095 | 0.7164 |
|
| 62 |
+
| 0.8461 | 4.0 | 4357 | 0.8722 | 0.7297 |
|
| 63 |
+
| 0.701 | 4.9998 | 5446 | 0.7641 | 0.7406 |
|
| 64 |
+
| 0.5977 | 5.9995 | 6535 | 0.6797 | 0.7490 |
|
| 65 |
+
| 0.5238 | 6.9993 | 7624 | 0.6209 | 0.7559 |
|
| 66 |
+
| 0.4742 | 8.0 | 8714 | 0.5837 | 0.7600 |
|
| 67 |
+
| 0.438 | 8.9998 | 9803 | 0.5532 | 0.7638 |
|
| 68 |
+
| 0.402 | 9.9995 | 10892 | 0.5331 | 0.7664 |
|
| 69 |
+
| 0.383 | 10.9993 | 11981 | 0.5156 | 0.7685 |
|
| 70 |
+
| 0.3627 | 12.0 | 13071 | 0.5070 | 0.7702 |
|
| 71 |
+
| 0.3521 | 12.9998 | 14160 | 0.4984 | 0.7714 |
|
| 72 |
+
| 0.344 | 13.9995 | 15249 | 0.4925 | 0.7722 |
|
| 73 |
+
| 0.3341 | 14.9993 | 16338 | 0.4847 | 0.7736 |
|
| 74 |
+
| 0.3275 | 16.0 | 17428 | 0.4808 | 0.7748 |
|
| 75 |
+
| 0.3223 | 16.9998 | 18517 | 0.4776 | 0.7751 |
|
| 76 |
+
| 0.3155 | 17.9995 | 19606 | 0.4804 | 0.7758 |
|
| 77 |
+
| 0.3033 | 18.9993 | 20695 | 0.4787 | 0.7761 |
|
| 78 |
+
| 0.2989 | 19.9954 | 21780 | 0.4756 | 0.7764 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- PEFT 0.5.0
|
| 84 |
+
- Transformers 4.40.2
|
| 85 |
+
- Pytorch 2.3.0
|
| 86 |
+
- Datasets 2.19.1
|
| 87 |
+
- Tokenizers 0.19.1
|