adediu25/distilbert-base-uncased-implicit-distilbert-all
Browse files- README.md +13 -17
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- runs/Apr16_22-57-15_0dafd0179a67/events.out.tfevents.1713308235.0dafd0179a67.1311.0 +3 -0
- runs/Apr16_23-20-35_0dafd0179a67/events.out.tfevents.1713309638.0dafd0179a67.1311.1 +3 -0
- tokenizer_config.json +0 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
|
|
8 |
model-index:
|
9 |
- name: trainer
|
10 |
results: []
|
@@ -17,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: {'accuracy': 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,32 +39,27 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.001
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.6693 | 5.0 | 25480 | 0.6674 | {'accuracy': 0.6136936111747194} |
|
57 |
-
| 0.6594 | 6.0 | 30576 | 0.6672 | {'accuracy': 0.6136936111747194} |
|
58 |
-
| 0.6663 | 7.0 | 35672 | 0.6682 | {'accuracy': 0.6136936111747194} |
|
59 |
-
| 0.6738 | 8.0 | 40768 | 0.6671 | {'accuracy': 0.6136936111747194} |
|
60 |
-
| 0.6669 | 9.0 | 45864 | 0.6671 | {'accuracy': 0.6136936111747194} |
|
61 |
-
| 0.6654 | 10.0 | 50960 | 0.6671 | {'accuracy': 0.6136936111747194} |
|
62 |
|
63 |
|
64 |
### Framework versions
|
65 |
|
|
|
66 |
- Transformers 4.38.2
|
67 |
- Pytorch 2.2.1+cu121
|
68 |
- Datasets 2.18.0
|
69 |
-
- Tokenizers 0.15.2
|
|
|
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: trainer
|
11 |
results: []
|
|
|
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: 0.6720
|
22 |
+
- Accuracy: {'accuracy': 0.7188000915960614}
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 0.001
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 4
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
|
53 |
+
| 0.5412 | 1.0 | 2772 | 0.7622 | {'accuracy': 0.6675062972292192} |
|
54 |
+
| 0.487 | 2.0 | 5544 | 0.7221 | {'accuracy': 0.6936111747194871} |
|
55 |
+
| 0.4486 | 3.0 | 8316 | 0.6913 | {'accuracy': 0.7105564460728189} |
|
56 |
+
| 0.4463 | 4.0 | 11088 | 0.6720 | {'accuracy': 0.7188000915960614} |
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
+
- PEFT 0.10.0
|
62 |
- Transformers 4.38.2
|
63 |
- Pytorch 2.2.1+cu121
|
64 |
- Datasets 2.18.0
|
65 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
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": 0.01,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_lin"
|
24 |
+
],
|
25 |
+
"task_type": "SEQ_CLS",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d424fe6766c67c4dd10cd3fd38e39a5785b36a33f08513614fef4bbec25875b
|
3 |
+
size 2669460
|
runs/Apr16_22-57-15_0dafd0179a67/events.out.tfevents.1713308235.0dafd0179a67.1311.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e8044498bb2cf32b85f5be410d3b35e6a644dd3e0ec7845e8f8905d2593f76a
|
3 |
+
size 7219
|
runs/Apr16_23-20-35_0dafd0179a67/events.out.tfevents.1713309638.0dafd0179a67.1311.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08b6bb7447451e8969a7d2fe482c3a5e7298ec8065c0da8df20f609697f53ee8
|
3 |
+
size 10704
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": "[PAD]",
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "[PAD]",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ce3a7a97684427bc85f4d0111668fb23ab0e9c616537d6875f075dabe150c7
|
3 |
size 4856
|