Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: led-large
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# led-large
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.1850
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 3e-05
|
| 36 |
+
- train_batch_size: 1
|
| 37 |
+
- eval_batch_size: 1
|
| 38 |
+
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 64
|
| 40 |
+
- total_train_batch_size: 64
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: polynomial
|
| 43 |
+
- lr_scheduler_warmup_steps: 500
|
| 44 |
+
- training_steps: 20000
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 0.1479 | 0.11 | 500 | 0.1901 |
|
| 52 |
+
| 0.1442 | 0.22 | 1000 | 0.1917 |
|
| 53 |
+
| 0.1466 | 0.33 | 1500 | 0.1959 |
|
| 54 |
+
| 0.1447 | 0.45 | 2000 | 0.1918 |
|
| 55 |
+
| 0.1633 | 0.56 | 2500 | 0.1874 |
|
| 56 |
+
| 0.171 | 0.67 | 3000 | 0.1849 |
|
| 57 |
+
| 0.1662 | 0.78 | 3500 | 0.1843 |
|
| 58 |
+
| 0.1743 | 0.89 | 4000 | 0.1837 |
|
| 59 |
+
| 0.1492 | 1.0 | 4500 | 0.1842 |
|
| 60 |
+
| 0.1515 | 1.11 | 5000 | 0.1849 |
|
| 61 |
+
| 0.1497 | 1.23 | 5500 | 0.1840 |
|
| 62 |
+
| 0.1515 | 1.34 | 6000 | 0.1839 |
|
| 63 |
+
| 0.1482 | 1.45 | 6500 | 0.1841 |
|
| 64 |
+
| 0.145 | 1.56 | 7000 | 0.1849 |
|
| 65 |
+
| 0.1467 | 1.67 | 7500 | 0.1824 |
|
| 66 |
+
| 0.1509 | 1.78 | 8000 | 0.1809 |
|
| 67 |
+
| 0.15 | 1.89 | 8500 | 0.1832 |
|
| 68 |
+
| 0.1383 | 2.01 | 9000 | 0.1831 |
|
| 69 |
+
| 0.1331 | 2.12 | 9500 | 0.1820 |
|
| 70 |
+
| 0.1406 | 2.23 | 10000 | 0.1830 |
|
| 71 |
+
| 0.1362 | 2.34 | 10500 | 0.1844 |
|
| 72 |
+
| 0.1373 | 2.45 | 11000 | 0.1836 |
|
| 73 |
+
| 0.1269 | 2.56 | 11500 | 0.1842 |
|
| 74 |
+
| 0.1362 | 2.67 | 12000 | 0.1819 |
|
| 75 |
+
| 0.14 | 2.79 | 12500 | 0.1832 |
|
| 76 |
+
| 0.1319 | 2.9 | 13000 | 0.1837 |
|
| 77 |
+
| 0.1304 | 3.01 | 13500 | 0.1845 |
|
| 78 |
+
| 0.1278 | 3.12 | 14000 | 0.1844 |
|
| 79 |
+
| 0.1235 | 3.23 | 14500 | 0.1832 |
|
| 80 |
+
| 0.1293 | 3.34 | 15000 | 0.1855 |
|
| 81 |
+
| 0.1302 | 3.45 | 15500 | 0.1836 |
|
| 82 |
+
| 0.1285 | 3.57 | 16000 | 0.1860 |
|
| 83 |
+
| 0.1274 | 3.68 | 16500 | 0.1860 |
|
| 84 |
+
| 0.1261 | 3.79 | 17000 | 0.1854 |
|
| 85 |
+
| 0.1304 | 3.9 | 17500 | 0.1859 |
|
| 86 |
+
| 0.1223 | 4.01 | 18000 | 0.1862 |
|
| 87 |
+
| 0.1235 | 4.12 | 18500 | 0.1849 |
|
| 88 |
+
| 0.1286 | 4.23 | 19000 | 0.1858 |
|
| 89 |
+
| 0.1186 | 4.35 | 19500 | 0.1856 |
|
| 90 |
+
| 0.1293 | 4.46 | 20000 | 0.1850 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- Transformers 4.37.2
|
| 96 |
+
- Pytorch 2.2.2+cu121
|
| 97 |
+
- Datasets 2.18.0
|
| 98 |
+
- Tokenizers 0.15.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.37.2"
|
| 8 |
+
}
|
logs/events.out.tfevents.1721233651.node0397.palmetto.clemson.edu.3180423.0
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 sha256:939fba5466c141b648d26345d838654000e591638072e3edc1803793175eb226
|
| 3 |
+
size 46931
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1839478364
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58a49cd659c2d79eaacfc0427b9c88c219f9ad25166e58831fd90909b65ba942
|
| 3 |
size 1839478364
|