End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: EleutherAI/polyglot-ko-1.3b
|
| 7 |
+
model-index:
|
| 8 |
+
- name: pretrain_w-cot_wo-asd
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# pretrain_w-cot_wo-asd
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2648
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 3e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 3
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 53 |
+
| 0.6934 | 0.1727 | 1000 | 0.2945 |
|
| 54 |
+
| 0.2864 | 0.3454 | 2000 | 0.2812 |
|
| 55 |
+
| 0.2787 | 0.5181 | 3000 | 0.2762 |
|
| 56 |
+
| 0.2739 | 0.6908 | 4000 | 0.2747 |
|
| 57 |
+
| 0.2709 | 0.8636 | 5000 | 0.2722 |
|
| 58 |
+
| 0.2727 | 1.0363 | 6000 | 0.2704 |
|
| 59 |
+
| 0.2694 | 1.2090 | 7000 | 0.2703 |
|
| 60 |
+
| 0.2684 | 1.3817 | 8000 | 0.2683 |
|
| 61 |
+
| 0.2652 | 1.5544 | 9000 | 0.2678 |
|
| 62 |
+
| 0.2641 | 1.7271 | 10000 | 0.2674 |
|
| 63 |
+
| 0.2624 | 1.8998 | 11000 | 0.2670 |
|
| 64 |
+
| 0.268 | 2.0725 | 12000 | 0.2661 |
|
| 65 |
+
| 0.2614 | 2.2453 | 13000 | 0.2661 |
|
| 66 |
+
| 0.2622 | 2.4180 | 14000 | 0.2656 |
|
| 67 |
+
| 0.2621 | 2.5907 | 15000 | 0.2653 |
|
| 68 |
+
| 0.263 | 2.7634 | 16000 | 0.2649 |
|
| 69 |
+
| 0.2625 | 2.9361 | 17000 | 0.2648 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.11.1
|
| 75 |
+
- Transformers 4.41.1
|
| 76 |
+
- Pytorch 2.3.0+cu121
|
| 77 |
+
- Datasets 2.19.1
|
| 78 |
+
- Tokenizers 0.19.1
|
runs/Jul30_21-37-22_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722343044.oem-WS-C621E-SAGE-Series.2701657.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8e7eef896eb4453e4a367b4dfa940bc00437f9871d304739368e00acb5c7238
|
| 3 |
+
size 13654
|