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_1e-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_1e-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: 6.7424
|
| 22 |
+
- Accuracy: 0.4188
|
| 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: 0.0001
|
| 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 |
+
| 1.9571 | 0.9985 | 341 | 3.9512 | 0.4538 |
|
| 60 |
+
| 1.8819 | 2.0 | 683 | 4.1128 | 0.4483 |
|
| 61 |
+
| 1.7702 | 2.9985 | 1024 | 4.3277 | 0.4461 |
|
| 62 |
+
| 1.6163 | 4.0 | 1366 | 4.5849 | 0.4424 |
|
| 63 |
+
| 1.4427 | 4.9985 | 1707 | 4.8503 | 0.4386 |
|
| 64 |
+
| 1.2498 | 6.0 | 2049 | 5.0926 | 0.4349 |
|
| 65 |
+
| 1.0655 | 6.9985 | 2390 | 5.2708 | 0.4326 |
|
| 66 |
+
| 0.8733 | 8.0 | 2732 | 5.4024 | 0.4317 |
|
| 67 |
+
| 0.7219 | 8.9985 | 3073 | 5.5348 | 0.4294 |
|
| 68 |
+
| 0.5932 | 10.0 | 3415 | 5.7690 | 0.4261 |
|
| 69 |
+
| 0.4719 | 10.9985 | 3756 | 5.8943 | 0.4254 |
|
| 70 |
+
| 0.3838 | 12.0 | 4098 | 6.0191 | 0.4247 |
|
| 71 |
+
| 0.329 | 12.9985 | 4439 | 6.1044 | 0.4246 |
|
| 72 |
+
| 0.2742 | 14.0 | 4781 | 6.1465 | 0.4216 |
|
| 73 |
+
| 0.2432 | 14.9985 | 5122 | 6.3254 | 0.4227 |
|
| 74 |
+
| 0.2158 | 16.0 | 5464 | 6.4410 | 0.4228 |
|
| 75 |
+
| 0.2013 | 16.9985 | 5805 | 6.3924 | 0.4215 |
|
| 76 |
+
| 0.1851 | 18.0 | 6147 | 6.5217 | 0.4201 |
|
| 77 |
+
| 0.1721 | 18.9985 | 6488 | 6.5573 | 0.4209 |
|
| 78 |
+
| 0.1676 | 20.0 | 6830 | 6.5661 | 0.4214 |
|
| 79 |
+
| 0.1579 | 20.9985 | 7171 | 6.5663 | 0.4213 |
|
| 80 |
+
| 0.1575 | 22.0 | 7513 | 6.6259 | 0.4202 |
|
| 81 |
+
| 0.15 | 22.9985 | 7854 | 6.5955 | 0.4214 |
|
| 82 |
+
| 0.1427 | 24.0 | 8196 | 6.6297 | 0.4216 |
|
| 83 |
+
| 0.145 | 24.9985 | 8537 | 6.5757 | 0.4227 |
|
| 84 |
+
| 0.1393 | 26.0 | 8879 | 6.5675 | 0.4213 |
|
| 85 |
+
| 0.1405 | 26.9985 | 9220 | 6.6650 | 0.4213 |
|
| 86 |
+
| 0.1365 | 28.0 | 9562 | 6.6427 | 0.4210 |
|
| 87 |
+
| 0.1372 | 28.9985 | 9903 | 6.5481 | 0.4209 |
|
| 88 |
+
| 0.134 | 30.0 | 10245 | 6.6617 | 0.4199 |
|
| 89 |
+
| 0.1287 | 30.9985 | 10586 | 6.6241 | 0.4207 |
|
| 90 |
+
| 0.1305 | 32.0 | 10928 | 6.6094 | 0.4199 |
|
| 91 |
+
| 0.1274 | 32.9985 | 11269 | 6.6823 | 0.4165 |
|
| 92 |
+
| 0.1296 | 34.0 | 11611 | 6.6210 | 0.4195 |
|
| 93 |
+
| 0.1271 | 34.9985 | 11952 | 6.7042 | 0.4185 |
|
| 94 |
+
| 0.1239 | 36.0 | 12294 | 6.6016 | 0.4204 |
|
| 95 |
+
| 0.1263 | 36.9985 | 12635 | 6.5736 | 0.4195 |
|
| 96 |
+
| 0.1234 | 38.0 | 12977 | 6.6094 | 0.4169 |
|
| 97 |
+
| 0.1236 | 38.9985 | 13318 | 6.6395 | 0.4151 |
|
| 98 |
+
| 0.1211 | 40.0 | 13660 | 6.6604 | 0.4132 |
|
| 99 |
+
| 0.1235 | 40.9985 | 14001 | 6.7098 | 0.4172 |
|
| 100 |
+
| 0.1206 | 42.0 | 14343 | 6.6072 | 0.4172 |
|
| 101 |
+
| 0.1165 | 42.9985 | 14684 | 6.7641 | 0.4178 |
|
| 102 |
+
| 0.1207 | 44.0 | 15026 | 6.6669 | 0.4187 |
|
| 103 |
+
| 0.1168 | 44.9985 | 15367 | 6.7258 | 0.4185 |
|
| 104 |
+
| 0.1194 | 46.0 | 15709 | 6.7819 | 0.4187 |
|
| 105 |
+
| 0.1179 | 46.9985 | 16050 | 6.7337 | 0.4189 |
|
| 106 |
+
| 0.1158 | 48.0 | 16392 | 6.7115 | 0.4196 |
|
| 107 |
+
| 0.1197 | 48.9985 | 16733 | 6.7568 | 0.4179 |
|
| 108 |
+
| 0.1163 | 49.9268 | 17050 | 6.7424 | 0.4188 |
|
| 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
|