bart-finetuned-lyrlen-256-tokens
Browse files- README.md +80 -0
- generation_config.json +13 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/bart-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bart-finetuned-lyrlen-256-tokens
|
| 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 |
+
# bart-finetuned-lyrlen-256-tokens
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.6246
|
| 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: 5e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 4
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 2.9847 | 0.17 | 500 | 2.7417 |
|
| 50 |
+
| 2.7603 | 0.33 | 1000 | 2.6936 |
|
| 51 |
+
| 2.6777 | 0.5 | 1500 | 2.7032 |
|
| 52 |
+
| 2.6679 | 0.67 | 2000 | 2.6790 |
|
| 53 |
+
| 2.631 | 0.83 | 2500 | 2.6584 |
|
| 54 |
+
| 2.612 | 1.0 | 3000 | 2.6528 |
|
| 55 |
+
| 2.5602 | 1.17 | 3500 | 2.7752 |
|
| 56 |
+
| 2.5321 | 1.33 | 4000 | 2.6442 |
|
| 57 |
+
| 2.523 | 1.5 | 4500 | 2.6168 |
|
| 58 |
+
| 2.5031 | 1.67 | 5000 | 2.6356 |
|
| 59 |
+
| 2.4454 | 1.83 | 5500 | 2.6987 |
|
| 60 |
+
| 2.5141 | 2.0 | 6000 | 2.6277 |
|
| 61 |
+
| 2.434 | 2.17 | 6500 | 2.6612 |
|
| 62 |
+
| 2.4381 | 2.33 | 7000 | 2.6339 |
|
| 63 |
+
| 2.4182 | 2.5 | 7500 | 2.6291 |
|
| 64 |
+
| 2.3564 | 2.67 | 8000 | 2.6309 |
|
| 65 |
+
| 2.4002 | 2.83 | 8500 | 2.5957 |
|
| 66 |
+
| 2.3692 | 3.0 | 9000 | 2.6150 |
|
| 67 |
+
| 2.4242 | 3.17 | 9500 | 2.5908 |
|
| 68 |
+
| 2.3854 | 3.33 | 10000 | 2.6053 |
|
| 69 |
+
| 2.3493 | 3.5 | 10500 | 2.6875 |
|
| 70 |
+
| 2.3231 | 3.67 | 11000 | 2.6197 |
|
| 71 |
+
| 2.3609 | 3.83 | 11500 | 2.6016 |
|
| 72 |
+
| 2.3651 | 4.0 | 12000 | 2.6246 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.40.0.dev0
|
| 78 |
+
- Pytorch 2.2.1+cu121
|
| 79 |
+
- Datasets 2.18.0
|
| 80 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.40.0.dev0"
|
| 13 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1625525396
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7607431db56e1ac60e737051731756a711546de498c4e809dd616bfa1624f870
|
| 3 |
size 1625525396
|