training completed[prod]: bart_baseline_peft
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: facebook/bart-large
|
| 7 |
+
model-index:
|
| 8 |
+
- name: bart_baseline_peft
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# bart_baseline_peft
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0693
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 2
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| No log | 0.18 | 250 | 1.1968 |
|
| 52 |
+
| 1.7053 | 0.35 | 500 | 1.1435 |
|
| 53 |
+
| 1.7053 | 0.53 | 750 | 1.1399 |
|
| 54 |
+
| 1.2238 | 0.71 | 1000 | 1.1146 |
|
| 55 |
+
| 1.2238 | 0.89 | 1250 | 1.1072 |
|
| 56 |
+
| 1.2006 | 1.06 | 1500 | 1.0856 |
|
| 57 |
+
| 1.2006 | 1.24 | 1750 | 1.0841 |
|
| 58 |
+
| 1.1399 | 1.42 | 2000 | 1.0757 |
|
| 59 |
+
| 1.1399 | 1.6 | 2250 | 1.0771 |
|
| 60 |
+
| 1.1393 | 1.77 | 2500 | 1.0709 |
|
| 61 |
+
| 1.1393 | 1.95 | 2750 | 1.0693 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- PEFT 0.10.0
|
| 67 |
+
- Transformers 4.38.2
|
| 68 |
+
- Pytorch 2.2.1+cu121
|
| 69 |
+
- Datasets 2.18.0
|
| 70 |
+
- Tokenizers 0.15.2
|
runs/Apr01_06-27-10_cf9f52a01f31/events.out.tfevents.1711952842.cf9f52a01f31.981.0
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:a842c5126ae2e2de25367d3e75c6b0499db18802f6249c4745a3011a984e7468
|
| 3 |
+
size 10172
|