End of training
Browse files- README.md +109 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: facebook/bart-large-cnn
|
3 |
+
library_name: peft
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: lora_fine_tuned_bart
|
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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nedith22-makerere-university/Fatima%20Fellowahip2024/runs/pvowwaid)
|
16 |
+
# lora_fine_tuned_bart
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6906
|
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: 4e-05
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 50
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 1.7253 | 1.0 | 32 | 1.8719 |
|
52 |
+
| 1.426 | 2.0 | 64 | 1.6167 |
|
53 |
+
| 1.3662 | 3.0 | 96 | 1.5225 |
|
54 |
+
| 1.3049 | 4.0 | 128 | 1.4695 |
|
55 |
+
| 1.2084 | 5.0 | 160 | 1.4319 |
|
56 |
+
| 1.2666 | 6.0 | 192 | 1.3709 |
|
57 |
+
| 1.2344 | 7.0 | 224 | 1.3053 |
|
58 |
+
| 1.1056 | 8.0 | 256 | 1.2560 |
|
59 |
+
| 1.025 | 9.0 | 288 | 1.1773 |
|
60 |
+
| 0.915 | 10.0 | 320 | 1.0743 |
|
61 |
+
| 0.8726 | 11.0 | 352 | 1.0085 |
|
62 |
+
| 0.8281 | 12.0 | 384 | 0.9630 |
|
63 |
+
| 0.777 | 13.0 | 416 | 0.9116 |
|
64 |
+
| 0.7681 | 14.0 | 448 | 0.8817 |
|
65 |
+
| 0.664 | 15.0 | 480 | 0.8357 |
|
66 |
+
| 0.6604 | 16.0 | 512 | 0.8077 |
|
67 |
+
| 0.6351 | 17.0 | 544 | 0.7837 |
|
68 |
+
| 0.6455 | 18.0 | 576 | 0.7724 |
|
69 |
+
| 0.6167 | 19.0 | 608 | 0.7585 |
|
70 |
+
| 0.5969 | 20.0 | 640 | 0.7443 |
|
71 |
+
| 0.5605 | 21.0 | 672 | 0.7382 |
|
72 |
+
| 0.5835 | 22.0 | 704 | 0.7302 |
|
73 |
+
| 0.5668 | 23.0 | 736 | 0.7183 |
|
74 |
+
| 0.575 | 24.0 | 768 | 0.7124 |
|
75 |
+
| 0.5319 | 25.0 | 800 | 0.7129 |
|
76 |
+
| 0.5515 | 26.0 | 832 | 0.7085 |
|
77 |
+
| 0.5219 | 27.0 | 864 | 0.7119 |
|
78 |
+
| 0.5509 | 28.0 | 896 | 0.7074 |
|
79 |
+
| 0.5172 | 29.0 | 928 | 0.7014 |
|
80 |
+
| 0.5298 | 30.0 | 960 | 0.7034 |
|
81 |
+
| 0.5071 | 31.0 | 992 | 0.6930 |
|
82 |
+
| 0.525 | 32.0 | 1024 | 0.6941 |
|
83 |
+
| 0.5153 | 33.0 | 1056 | 0.6963 |
|
84 |
+
| 0.5115 | 34.0 | 1088 | 0.6925 |
|
85 |
+
| 0.5194 | 35.0 | 1120 | 0.6933 |
|
86 |
+
| 0.5138 | 36.0 | 1152 | 0.6926 |
|
87 |
+
| 0.4649 | 37.0 | 1184 | 0.6913 |
|
88 |
+
| 0.5127 | 38.0 | 1216 | 0.6932 |
|
89 |
+
| 0.5044 | 39.0 | 1248 | 0.6929 |
|
90 |
+
| 0.4701 | 40.0 | 1280 | 0.6921 |
|
91 |
+
| 0.5156 | 41.0 | 1312 | 0.6931 |
|
92 |
+
| 0.5163 | 42.0 | 1344 | 0.6898 |
|
93 |
+
| 0.5153 | 43.0 | 1376 | 0.6896 |
|
94 |
+
| 0.5054 | 44.0 | 1408 | 0.6880 |
|
95 |
+
| 0.4915 | 45.0 | 1440 | 0.6872 |
|
96 |
+
| 0.4908 | 46.0 | 1472 | 0.6879 |
|
97 |
+
| 0.4836 | 47.0 | 1504 | 0.6891 |
|
98 |
+
| 0.491 | 48.0 | 1536 | 0.6889 |
|
99 |
+
| 0.4814 | 49.0 | 1568 | 0.6905 |
|
100 |
+
| 0.4872 | 50.0 | 1600 | 0.6906 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- PEFT 0.12.0
|
106 |
+
- Transformers 4.42.3
|
107 |
+
- Pytorch 2.1.2
|
108 |
+
- Datasets 2.20.0
|
109 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/bart-large-cnn",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "SEQ_2_SEQ_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a66999fd85d6206944cba511b37b4e7e3a6998b6f15da76c49fa03980e642a2c
|
3 |
+
size 18894856
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:135cbb658c9381de91ca2891673db1137bd5573962f0ce8d3c59472e01b9b473
|
3 |
+
size 5112
|