End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gogamza/kobart-base-v2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: KoBART_base_v2-trial
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# KoBART_base_v2-trial
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1815
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0005
|
| 38 |
+
- train_batch_size: 64
|
| 39 |
+
- eval_batch_size: 64
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- lr_scheduler_warmup_steps: 20
|
| 44 |
+
- num_epochs: 3
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.4147 | 0.11 | 50 | 0.5490 |
|
| 52 |
+
| 0.5457 | 0.22 | 100 | 0.4810 |
|
| 53 |
+
| 0.4642 | 0.32 | 150 | 0.3971 |
|
| 54 |
+
| 0.4364 | 0.43 | 200 | 0.3955 |
|
| 55 |
+
| 0.4111 | 0.54 | 250 | 0.3851 |
|
| 56 |
+
| 0.3888 | 0.65 | 300 | 0.3438 |
|
| 57 |
+
| 0.3586 | 0.76 | 350 | 0.3290 |
|
| 58 |
+
| 0.3304 | 0.87 | 400 | 0.3201 |
|
| 59 |
+
| 0.3337 | 0.97 | 450 | 0.2992 |
|
| 60 |
+
| 0.2677 | 1.08 | 500 | 0.3161 |
|
| 61 |
+
| 0.2576 | 1.19 | 550 | 0.2981 |
|
| 62 |
+
| 0.2467 | 1.3 | 600 | 0.2846 |
|
| 63 |
+
| 0.2369 | 1.41 | 650 | 0.2674 |
|
| 64 |
+
| 0.226 | 1.52 | 700 | 0.2529 |
|
| 65 |
+
| 0.2204 | 1.62 | 750 | 0.2446 |
|
| 66 |
+
| 0.204 | 1.73 | 800 | 0.2400 |
|
| 67 |
+
| 0.2071 | 1.84 | 850 | 0.2262 |
|
| 68 |
+
| 0.1911 | 1.95 | 900 | 0.2153 |
|
| 69 |
+
| 0.1591 | 2.06 | 950 | 0.2121 |
|
| 70 |
+
| 0.1338 | 2.16 | 1000 | 0.2090 |
|
| 71 |
+
| 0.1312 | 2.27 | 1050 | 0.1986 |
|
| 72 |
+
| 0.1336 | 2.38 | 1100 | 0.1947 |
|
| 73 |
+
| 0.1205 | 2.49 | 1150 | 0.1903 |
|
| 74 |
+
| 0.1162 | 2.6 | 1200 | 0.1867 |
|
| 75 |
+
| 0.1187 | 2.71 | 1250 | 0.1840 |
|
| 76 |
+
| 0.1171 | 2.81 | 1300 | 0.1821 |
|
| 77 |
+
| 0.1149 | 2.92 | 1350 | 0.1815 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.36.0
|
| 83 |
+
- Pytorch 2.0.1+cu117
|
| 84 |
+
- Datasets 2.15.0
|
| 85 |
+
- Tokenizers 0.15.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"forced_eos_token_id": 1,
|
| 7 |
+
"pad_token_id": 3,
|
| 8 |
+
"transformers_version": "4.36.0"
|
| 9 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 495589768
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34874bc55cf751b3eabe532f23280afb152403cf7dd7ada7277ed3dfc7c9079
|
| 3 |
size 495589768
|
runs/Dec19_11-09-00_e64a5fb166fb/events.out.tfevents.1702951741.e64a5fb166fb.8679.1
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:a086ed300fa944ebbe7c5afc4cd791dc06f161b0661e853a221f7f9bc976294d
|
| 3 |
+
size 17179
|