Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wikipedia_13
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wikipedia_13
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.9275
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0001
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 13
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 32
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 40000
|
| 45 |
+
- training_steps: 100000
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-------:|:------:|:---------------:|
|
| 52 |
+
| No log | 1.4657 | 2000 | 8.0872 |
|
| 53 |
+
| 8.1326 | 2.9315 | 4000 | 7.3975 |
|
| 54 |
+
| 8.1326 | 4.3972 | 6000 | 7.2718 |
|
| 55 |
+
| 7.2846 | 5.8630 | 8000 | 7.1835 |
|
| 56 |
+
| 7.2846 | 7.3287 | 10000 | 7.0992 |
|
| 57 |
+
| 7.1078 | 8.7944 | 12000 | 7.0331 |
|
| 58 |
+
| 7.1078 | 10.2602 | 14000 | 6.9494 |
|
| 59 |
+
| 6.942 | 11.7259 | 16000 | 6.8899 |
|
| 60 |
+
| 6.942 | 13.1916 | 18000 | 6.7822 |
|
| 61 |
+
| 6.7676 | 14.6574 | 20000 | 6.7185 |
|
| 62 |
+
| 6.7676 | 16.1231 | 22000 | 6.6536 |
|
| 63 |
+
| 6.5959 | 17.5889 | 24000 | 6.5431 |
|
| 64 |
+
| 6.5959 | 19.0546 | 26000 | 6.3925 |
|
| 65 |
+
| 6.3624 | 20.5203 | 28000 | 6.2119 |
|
| 66 |
+
| 6.3624 | 21.9861 | 30000 | 5.9526 |
|
| 67 |
+
| 5.9309 | 23.4518 | 32000 | 5.4162 |
|
| 68 |
+
| 5.9309 | 24.9176 | 34000 | 5.0255 |
|
| 69 |
+
| 5.0575 | 26.3833 | 36000 | 4.7680 |
|
| 70 |
+
| 5.0575 | 27.8490 | 38000 | 4.5020 |
|
| 71 |
+
| 4.5282 | 29.3148 | 40000 | 4.3214 |
|
| 72 |
+
| 4.5282 | 30.7805 | 42000 | 4.1312 |
|
| 73 |
+
| 4.1335 | 32.2462 | 44000 | 3.9708 |
|
| 74 |
+
| 4.1335 | 33.7120 | 46000 | 3.8616 |
|
| 75 |
+
| 3.8339 | 35.1777 | 48000 | 3.7640 |
|
| 76 |
+
| 3.8339 | 36.6435 | 50000 | 3.7074 |
|
| 77 |
+
| 3.6042 | 38.1092 | 52000 | 3.6360 |
|
| 78 |
+
| 3.6042 | 39.5749 | 54000 | 3.5203 |
|
| 79 |
+
| 3.4291 | 41.0407 | 56000 | 3.4424 |
|
| 80 |
+
| 3.4291 | 42.5064 | 58000 | 3.4276 |
|
| 81 |
+
| 3.286 | 43.9722 | 60000 | 3.3797 |
|
| 82 |
+
| 3.286 | 45.4379 | 62000 | 3.3277 |
|
| 83 |
+
| 3.1748 | 46.9036 | 64000 | 3.2922 |
|
| 84 |
+
| 3.1748 | 48.3694 | 66000 | 3.2361 |
|
| 85 |
+
| 3.0842 | 49.8351 | 68000 | 3.2043 |
|
| 86 |
+
| 3.0842 | 51.3008 | 70000 | 3.1870 |
|
| 87 |
+
| 3.0082 | 52.7666 | 72000 | 3.1487 |
|
| 88 |
+
| 3.0082 | 54.2323 | 74000 | 3.1257 |
|
| 89 |
+
| 2.9483 | 55.6981 | 76000 | 3.1001 |
|
| 90 |
+
| 2.9483 | 57.1638 | 78000 | 3.0694 |
|
| 91 |
+
| 2.8885 | 58.6295 | 80000 | 3.0605 |
|
| 92 |
+
| 2.8885 | 60.0953 | 82000 | 3.0568 |
|
| 93 |
+
| 2.8416 | 61.5610 | 84000 | 3.0083 |
|
| 94 |
+
| 2.8416 | 63.0267 | 86000 | 3.0188 |
|
| 95 |
+
| 2.8064 | 64.4925 | 88000 | 3.0213 |
|
| 96 |
+
| 2.8064 | 65.9582 | 90000 | 2.9645 |
|
| 97 |
+
| 2.7717 | 67.4240 | 92000 | 2.9901 |
|
| 98 |
+
| 2.7717 | 68.8897 | 94000 | 2.9684 |
|
| 99 |
+
| 2.7441 | 70.3554 | 96000 | 2.9565 |
|
| 100 |
+
| 2.7441 | 71.8212 | 98000 | 2.9547 |
|
| 101 |
+
| 2.7289 | 73.2869 | 100000 | 2.9275 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.45.2
|
| 107 |
+
- Pytorch 2.5.1+cu124
|
| 108 |
+
- Datasets 3.0.1
|
| 109 |
+
- Tokenizers 0.20.1
|