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_doc_qa_Qwen_Qwen1.5-4B_3e-5_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_doc_qa_Qwen_Qwen1.5-4B_3e-5_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: 3.5856
|
| 22 |
+
- Accuracy: 0.5001
|
| 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: 3e-05
|
| 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 |
+
| 1.7766 | 0.9998 | 1089 | 2.3352 | 0.5155 |
|
| 60 |
+
| 1.7291 | 1.9995 | 2178 | 2.3047 | 0.5177 |
|
| 61 |
+
| 1.6609 | 2.9993 | 3267 | 2.3113 | 0.5187 |
|
| 62 |
+
| 1.6108 | 4.0 | 4357 | 2.3487 | 0.518 |
|
| 63 |
+
| 1.5489 | 4.9998 | 5446 | 2.3843 | 0.5161 |
|
| 64 |
+
| 1.5093 | 5.9995 | 6535 | 2.4637 | 0.5138 |
|
| 65 |
+
| 1.4364 | 6.9993 | 7624 | 2.5600 | 0.5108 |
|
| 66 |
+
| 1.4038 | 8.0 | 8714 | 2.6166 | 0.5105 |
|
| 67 |
+
| 1.3439 | 8.9998 | 9803 | 2.7111 | 0.5092 |
|
| 68 |
+
| 1.2928 | 9.9995 | 10892 | 2.8851 | 0.5062 |
|
| 69 |
+
| 1.2284 | 10.9993 | 11981 | 2.9595 | 0.5042 |
|
| 70 |
+
| 1.2142 | 12.0 | 13071 | 3.0894 | 0.5034 |
|
| 71 |
+
| 1.1791 | 12.9998 | 14160 | 3.1358 | 0.5024 |
|
| 72 |
+
| 1.1272 | 13.9995 | 15249 | 3.2272 | 0.5017 |
|
| 73 |
+
| 1.0934 | 14.9993 | 16338 | 3.3488 | 0.5001 |
|
| 74 |
+
| 1.0586 | 16.0 | 17428 | 3.4072 | 0.5015 |
|
| 75 |
+
| 1.0415 | 16.9998 | 18517 | 3.4943 | 0.5009 |
|
| 76 |
+
| 1.011 | 17.9995 | 19606 | 3.5465 | 0.5001 |
|
| 77 |
+
| 1.0036 | 18.9993 | 20695 | 3.5320 | 0.5011 |
|
| 78 |
+
| 0.9595 | 19.9954 | 21780 | 3.5856 | 0.5001 |
|
| 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
|