Commit
•
d2531aa
1
Parent(s):
f4575a7
bart-finetuned-lyrlen-512-tokens
Browse files- README.md +104 -0
- generation_config.json +13 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-512-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-512-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: 1.8349
|
| 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: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 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 |
+
| 2.3484 | 0.08 | 500 | 2.0373 |
|
| 50 |
+
| 2.0389 | 0.17 | 1000 | 1.9391 |
|
| 51 |
+
| 2.0181 | 0.25 | 1500 | 1.9070 |
|
| 52 |
+
| 1.9238 | 0.33 | 2000 | 1.9121 |
|
| 53 |
+
| 1.9005 | 0.42 | 2500 | 1.8966 |
|
| 54 |
+
| 1.8814 | 0.5 | 3000 | 1.8816 |
|
| 55 |
+
| 1.8839 | 0.58 | 3500 | 1.8806 |
|
| 56 |
+
| 1.8251 | 0.67 | 4000 | 1.9091 |
|
| 57 |
+
| 1.8454 | 0.75 | 4500 | 1.8798 |
|
| 58 |
+
| 1.8264 | 0.83 | 5000 | 1.8769 |
|
| 59 |
+
| 1.8545 | 0.92 | 5500 | 1.8511 |
|
| 60 |
+
| 1.8335 | 1.0 | 6000 | 1.9010 |
|
| 61 |
+
| 1.8184 | 1.08 | 6500 | 1.8511 |
|
| 62 |
+
| 1.7887 | 1.17 | 7000 | 1.8472 |
|
| 63 |
+
| 1.7811 | 1.25 | 7500 | 1.8341 |
|
| 64 |
+
| 1.7388 | 1.33 | 8000 | 1.8912 |
|
| 65 |
+
| 1.7981 | 1.42 | 8500 | 1.8615 |
|
| 66 |
+
| 1.7849 | 1.5 | 9000 | 1.8405 |
|
| 67 |
+
| 1.7814 | 1.58 | 9500 | 1.8314 |
|
| 68 |
+
| 1.7568 | 1.67 | 10000 | 1.8449 |
|
| 69 |
+
| 1.7061 | 1.75 | 10500 | 1.8545 |
|
| 70 |
+
| 1.7169 | 1.83 | 11000 | 1.8361 |
|
| 71 |
+
| 1.7019 | 1.92 | 11500 | 1.8479 |
|
| 72 |
+
| 1.727 | 2.0 | 12000 | 1.8741 |
|
| 73 |
+
| 1.7035 | 2.08 | 12500 | 1.8518 |
|
| 74 |
+
| 1.7134 | 2.17 | 13000 | 1.8361 |
|
| 75 |
+
| 1.6809 | 2.25 | 13500 | 1.8279 |
|
| 76 |
+
| 1.7093 | 2.33 | 14000 | 1.8428 |
|
| 77 |
+
| 1.7437 | 2.42 | 14500 | 1.8424 |
|
| 78 |
+
| 1.6968 | 2.5 | 15000 | 1.8325 |
|
| 79 |
+
| 1.661 | 2.58 | 15500 | 1.8337 |
|
| 80 |
+
| 1.6542 | 2.67 | 16000 | 1.8282 |
|
| 81 |
+
| 1.6607 | 2.75 | 16500 | 1.8300 |
|
| 82 |
+
| 1.6427 | 2.83 | 17000 | 1.8389 |
|
| 83 |
+
| 1.6821 | 2.92 | 17500 | 1.8242 |
|
| 84 |
+
| 1.6968 | 3.0 | 18000 | 1.8376 |
|
| 85 |
+
| 1.6716 | 3.08 | 18500 | 1.8302 |
|
| 86 |
+
| 1.6706 | 3.17 | 19000 | 1.8326 |
|
| 87 |
+
| 1.622 | 3.25 | 19500 | 1.8246 |
|
| 88 |
+
| 1.6802 | 3.33 | 20000 | 1.8345 |
|
| 89 |
+
| 1.6321 | 3.42 | 20500 | 1.8499 |
|
| 90 |
+
| 1.6832 | 3.5 | 21000 | 1.8394 |
|
| 91 |
+
| 1.6223 | 3.58 | 21500 | 1.8329 |
|
| 92 |
+
| 1.6831 | 3.67 | 22000 | 1.8408 |
|
| 93 |
+
| 1.6455 | 3.75 | 22500 | 1.8336 |
|
| 94 |
+
| 1.64 | 3.83 | 23000 | 1.8372 |
|
| 95 |
+
| 1.663 | 3.92 | 23500 | 1.8340 |
|
| 96 |
+
| 1.6 | 4.0 | 24000 | 1.8349 |
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
### Framework versions
|
| 100 |
+
|
| 101 |
+
- Transformers 4.38.2
|
| 102 |
+
- Pytorch 2.2.1+cu121
|
| 103 |
+
- Datasets 2.18.0
|
| 104 |
+
- 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": "4.38.2"
|
| 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:b35e809209c16bf75d13efda990596125db677726a9b5be849bc3eb15e7c6c7f
|
| 3 |
size 1625525396
|