End of training
Browse files- README.md +71 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- runs/Feb25_13-08-36_1ffb6ab2c5f9/events.out.tfevents.1708866518.1ffb6ab2c5f9.34.0 +3 -0
- runs/Feb25_13-12-05_1ffb6ab2c5f9/events.out.tfevents.1708866726.1ffb6ab2c5f9.34.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
base_model: distilbert-base-uncased
|
9 |
+
model-index:
|
10 |
+
- name: distilbert-base-uncased-lora-imdb-sentiment
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# distilbert-base-uncased-lora-imdb-sentiment
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6932
|
22 |
+
- Accuracy: 0.4968
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.001
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 10
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 0.6937 | 1.0 | 7500 | 0.6977 | 0.5032 |
|
54 |
+
| 0.6952 | 2.0 | 15000 | 0.6931 | 0.5032 |
|
55 |
+
| 0.6933 | 3.0 | 22500 | 0.6933 | 0.4968 |
|
56 |
+
| 0.6933 | 4.0 | 30000 | 0.6931 | 0.5032 |
|
57 |
+
| 0.6932 | 5.0 | 37500 | 0.6931 | 0.5032 |
|
58 |
+
| 0.6933 | 6.0 | 45000 | 0.6932 | 0.4968 |
|
59 |
+
| 0.6931 | 7.0 | 52500 | 0.6932 | 0.4968 |
|
60 |
+
| 0.6933 | 8.0 | 60000 | 0.6931 | 0.5032 |
|
61 |
+
| 0.6931 | 9.0 | 67500 | 0.6932 | 0.4968 |
|
62 |
+
| 0.6932 | 10.0 | 75000 | 0.6932 | 0.4968 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- PEFT 0.8.2
|
68 |
+
- Transformers 4.37.2
|
69 |
+
- Pytorch 2.1.0+cu121
|
70 |
+
- Datasets 2.17.1
|
71 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "distilbert-base-uncased",
|
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 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.01,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 4,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"lin2",
|
23 |
+
"lin1",
|
24 |
+
"out_lin",
|
25 |
+
"q_lin",
|
26 |
+
"classifier",
|
27 |
+
"k_lin",
|
28 |
+
"v_lin",
|
29 |
+
"pre_classifier"
|
30 |
+
],
|
31 |
+
"task_type": "SEQ_CLS",
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f185f9b120fc691757bc9968535c93552a160707f4bd126b0b93a261ac7317ea
|
3 |
+
size 3818408
|
runs/Feb25_13-08-36_1ffb6ab2c5f9/events.out.tfevents.1708866518.1ffb6ab2c5f9.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:228237f3765766e113e02cfb46212b7f8daab4ab907c5ba1fe5334489206d3ab
|
3 |
+
size 4761
|
runs/Feb25_13-12-05_1ffb6ab2c5f9/events.out.tfevents.1708866726.1ffb6ab2c5f9.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c57b003486c7f17c1f28c71ed983262fc58cd41c050f9c545ded34afee6bb56c
|
3 |
+
size 31989
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100": {
|
13 |
+
"content": "[UNK]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"101": {
|
21 |
+
"content": "[CLS]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"102": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"103": {
|
37 |
+
"content": "[MASK]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c7fb200f881cb6a29c9774853e23d3d8b1063a4ef072754f1439637c0312251
|
3 |
+
size 4792
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|