Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: hyunwoongko/kobart
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: qa_kor_math_2
|
| 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 |
+
# qa_kor_math_2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [hyunwoongko/kobart](https://huggingface.co/hyunwoongko/kobart) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1234
|
| 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: 1e-05
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 16
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 400
|
| 44 |
+
- num_epochs: 20
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| No log | 0.56 | 100 | 3.2887 |
|
| 51 |
+
| No log | 1.13 | 200 | 0.8359 |
|
| 52 |
+
| No log | 1.69 | 300 | 0.4944 |
|
| 53 |
+
| No log | 2.26 | 400 | 0.3843 |
|
| 54 |
+
| 2.4704 | 2.82 | 500 | 0.3349 |
|
| 55 |
+
| 2.4704 | 3.39 | 600 | 0.3005 |
|
| 56 |
+
| 2.4704 | 3.95 | 700 | 0.2768 |
|
| 57 |
+
| 2.4704 | 4.52 | 800 | 0.2641 |
|
| 58 |
+
| 2.4704 | 5.08 | 900 | 0.2479 |
|
| 59 |
+
| 0.3213 | 5.65 | 1000 | 0.2335 |
|
| 60 |
+
| 0.3213 | 6.21 | 1100 | 0.2208 |
|
| 61 |
+
| 0.3213 | 6.78 | 1200 | 0.2117 |
|
| 62 |
+
| 0.3213 | 7.34 | 1300 | 0.2041 |
|
| 63 |
+
| 0.3213 | 7.91 | 1400 | 0.1964 |
|
| 64 |
+
| 0.2503 | 8.47 | 1500 | 0.1876 |
|
| 65 |
+
| 0.2503 | 9.04 | 1600 | 0.1790 |
|
| 66 |
+
| 0.2503 | 9.6 | 1700 | 0.1745 |
|
| 67 |
+
| 0.2503 | 10.17 | 1800 | 0.1673 |
|
| 68 |
+
| 0.2503 | 10.73 | 1900 | 0.1623 |
|
| 69 |
+
| 0.2141 | 11.3 | 2000 | 0.1579 |
|
| 70 |
+
| 0.2141 | 11.86 | 2100 | 0.1527 |
|
| 71 |
+
| 0.2141 | 12.43 | 2200 | 0.1494 |
|
| 72 |
+
| 0.2141 | 12.99 | 2300 | 0.1438 |
|
| 73 |
+
| 0.2141 | 13.56 | 2400 | 0.1427 |
|
| 74 |
+
| 0.1873 | 14.12 | 2500 | 0.1386 |
|
| 75 |
+
| 0.1873 | 14.69 | 2600 | 0.1347 |
|
| 76 |
+
| 0.1873 | 15.25 | 2700 | 0.1334 |
|
| 77 |
+
| 0.1873 | 15.82 | 2800 | 0.1321 |
|
| 78 |
+
| 0.1873 | 16.38 | 2900 | 0.1295 |
|
| 79 |
+
| 0.1718 | 16.95 | 3000 | 0.1276 |
|
| 80 |
+
| 0.1718 | 17.51 | 3100 | 0.1263 |
|
| 81 |
+
| 0.1718 | 18.08 | 3200 | 0.1255 |
|
| 82 |
+
| 0.1718 | 18.64 | 3300 | 0.1244 |
|
| 83 |
+
| 0.1718 | 19.21 | 3400 | 0.1240 |
|
| 84 |
+
| 0.1628 | 19.77 | 3500 | 0.1234 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.38.2
|
| 90 |
+
- Pytorch 2.2.1+cu121
|
| 91 |
+
- Datasets 2.18.0
|
| 92 |
+
- Tokenizers 0.15.2
|
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": "4.38.2"
|
| 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 sha256:97df9a2107900f429d3c6bd1f58b5be426b4c781c89fa2a65f509a025711bcf8
|
| 3 |
size 495589768
|
runs/Apr15_23-33-52_90b259ddbe02/events.out.tfevents.1713224037.90b259ddbe02.2087.0
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 sha256:67dccfaed79cf58099df1a5d7b3557774e23352934eb03f93643554d2d97a57b
|
| 3 |
+
size 16799
|