ashwaninbs
commited on
Commit
•
7cbb21a
1
Parent(s):
3abfa0f
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: ashwaninbs/bart-cnn-samsum-finetuned
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- samsum
|
8 |
+
model-index:
|
9 |
+
- name: bart-cnn-samsum-peft
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# bart-cnn-samsum-peft
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [ashwaninbs/bart-cnn-samsum-finetuned](https://huggingface.co/ashwaninbs/bart-cnn-samsum-finetuned) on the samsum dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1319
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 1e-05
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 5
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 0.0661 | 1.0 | 74 | 0.1318 |
|
52 |
+
| 0.0869 | 2.0 | 148 | 0.1319 |
|
53 |
+
| 0.0604 | 3.0 | 222 | 0.1318 |
|
54 |
+
| 0.0749 | 4.0 | 296 | 0.1319 |
|
55 |
+
| 0.0737 | 5.0 | 370 | 0.1319 |
|
56 |
+
|
57 |
+
|
58 |
+
### Framework versions
|
59 |
+
|
60 |
+
- Transformers 4.35.0
|
61 |
+
- Pytorch 2.1.0+cu118
|
62 |
+
- Datasets 2.14.6
|
63 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "ashwaninbs/bart-cnn-samsum-finetuned",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 32,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "SEQ_2_SEQ_LM"
|
23 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbec439ceb3751ad95c269e18434f8ee33e470ab018565fb308a3b7171977d01
|
3 |
+
size 18894856
|
runs/Nov09_21-36-14_da0a795be2f5/events.out.tfevents.1699565789.da0a795be2f5.1803.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcc7187aa6b27d467d0842dcea6f584846016bdee88e3ceaf2bd1e8e50533dd8
|
3 |
+
size 23138
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0e3bdf8424ee13f5fdc40a19ac6dd4ad88f3c38fc3c225489c4e962aa73d005
|
3 |
+
size 4600
|