abhishekkumaribt
commited on
Commit
•
2d2facc
1
Parent(s):
156f0a6
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: bert-base-cased
|
3 |
+
library_name: peft
|
4 |
+
license: apache-2.0
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: bert-lora
|
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 |
+
# bert-lora
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4540
|
22 |
+
- Accuracy: 0.78
|
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: 5e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 15
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| No log | 1.0 | 125 | 0.6659 | 0.64 |
|
54 |
+
| No log | 2.0 | 250 | 0.6518 | 0.64 |
|
55 |
+
| No log | 3.0 | 375 | 0.6353 | 0.66 |
|
56 |
+
| 0.6613 | 4.0 | 500 | 0.6126 | 0.7 |
|
57 |
+
| 0.6613 | 5.0 | 625 | 0.5862 | 0.7 |
|
58 |
+
| 0.6613 | 6.0 | 750 | 0.5677 | 0.68 |
|
59 |
+
| 0.6613 | 7.0 | 875 | 0.5350 | 0.72 |
|
60 |
+
| 0.5607 | 8.0 | 1000 | 0.5163 | 0.74 |
|
61 |
+
| 0.5607 | 9.0 | 1125 | 0.4980 | 0.74 |
|
62 |
+
| 0.5607 | 10.0 | 1250 | 0.4821 | 0.75 |
|
63 |
+
| 0.5607 | 11.0 | 1375 | 0.4738 | 0.77 |
|
64 |
+
| 0.4757 | 12.0 | 1500 | 0.4633 | 0.78 |
|
65 |
+
| 0.4757 | 13.0 | 1625 | 0.4574 | 0.78 |
|
66 |
+
| 0.4757 | 14.0 | 1750 | 0.4553 | 0.78 |
|
67 |
+
| 0.4757 | 15.0 | 1875 | 0.4540 | 0.78 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- PEFT 0.13.0
|
73 |
+
- Transformers 4.44.2
|
74 |
+
- Pytorch 2.4.1+cu121
|
75 |
+
- Datasets 3.0.1
|
76 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bert-base-cased",
|
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": 1,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"classifier",
|
19 |
+
"score"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 1,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"query",
|
27 |
+
"value"
|
28 |
+
],
|
29 |
+
"task_type": "SEQ_CLS",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5ec926816527d6b1b0f5f96b602ff1c22fbde65850031915f79e9fbb7b9a9b0
|
3 |
+
size 160400
|
runs/Oct06_15-38-25_5ee937f6ced0/events.out.tfevents.1728229108.5ee937f6ced0.553.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88d9eb5608368e102d6e403df377a9f44ef008637c0fe6d57131bb45068cf2c1
|
3 |
+
size 5239
|
runs/Oct06_15-40-17_5ee937f6ced0/events.out.tfevents.1728229219.5ee937f6ced0.553.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92f3fa02c65a2619fa96973fd50b12b28f9cd782803e0f44fb62a58835ba1a31
|
3 |
+
size 10748
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d208f81c7c90af174ee2313b21f271a672995210572724592ebacfc105dd5856
|
3 |
+
size 5176
|