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_nq_train6000_eval6489_v1_recite_qa_v3_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_nq_train6000_eval6489_v1_recite_qa_v3_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: 0.4311
|
| 22 |
+
- Accuracy: 0.7981
|
| 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 |
+
| 1.7637 | 1.0 | 529 | 1.4995 | 0.6288 |
|
| 60 |
+
| 1.3986 | 2.0 | 1058 | 1.1711 | 0.6720 |
|
| 61 |
+
| 0.9515 | 3.0 | 1587 | 0.8766 | 0.7148 |
|
| 62 |
+
| 0.642 | 4.0 | 2116 | 0.6720 | 0.7478 |
|
| 63 |
+
| 0.4362 | 5.0 | 2645 | 0.5458 | 0.7697 |
|
| 64 |
+
| 0.3201 | 6.0 | 3174 | 0.4751 | 0.7823 |
|
| 65 |
+
| 0.2652 | 7.0 | 3703 | 0.4510 | 0.7887 |
|
| 66 |
+
| 0.2263 | 8.0 | 4232 | 0.4372 | 0.7914 |
|
| 67 |
+
| 0.2035 | 9.0 | 4761 | 0.4335 | 0.7940 |
|
| 68 |
+
| 0.1913 | 10.0 | 5290 | 0.4322 | 0.7950 |
|
| 69 |
+
| 0.188 | 11.0 | 5819 | 0.4379 | 0.7945 |
|
| 70 |
+
| 0.1777 | 12.0 | 6348 | 0.4279 | 0.7957 |
|
| 71 |
+
| 0.1723 | 13.0 | 6877 | 0.4326 | 0.7956 |
|
| 72 |
+
| 0.1767 | 14.0 | 7406 | 0.4329 | 0.7967 |
|
| 73 |
+
| 0.1666 | 15.0 | 7935 | 0.4396 | 0.7962 |
|
| 74 |
+
| 0.1642 | 16.0 | 8464 | 0.4391 | 0.7965 |
|
| 75 |
+
| 0.1575 | 17.0 | 8993 | 0.4405 | 0.7967 |
|
| 76 |
+
| 0.1634 | 18.0 | 9522 | 0.4265 | 0.7976 |
|
| 77 |
+
| 0.1593 | 19.0 | 10051 | 0.4323 | 0.7978 |
|
| 78 |
+
| 0.153 | 20.0 | 10580 | 0.4311 | 0.7981 |
|
| 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
|