Model save
Browse files
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: bert-base-uncased
|
3 |
+
library_name: peft
|
4 |
+
license: apache-2.0
|
5 |
+
metrics:
|
6 |
+
- f1
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
tags:
|
11 |
+
- generated_from_trainer
|
12 |
+
model-index:
|
13 |
+
- name: Bert-v1
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# Bert-v1
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.4553
|
25 |
+
- F1: 0.9691
|
26 |
+
- Accuracy: 0.94
|
27 |
+
- Precision: 0.94
|
28 |
+
- Recall: 1.0
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 0.002
|
48 |
+
- train_batch_size: 1
|
49 |
+
- eval_batch_size: 8
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- training_steps: 10
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | Precision | Recall |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:---------:|:------:|
|
59 |
+
| 0.8405 | 0.001 | 1 | 0.3011 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
60 |
+
| 0.2944 | 0.002 | 2 | 0.2259 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
61 |
+
| 0.0869 | 0.003 | 3 | 0.2497 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
62 |
+
| 0.056 | 0.004 | 4 | 0.3000 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
63 |
+
| 0.0137 | 0.005 | 5 | 0.3494 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
64 |
+
| 0.0028 | 0.006 | 6 | 0.3885 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
65 |
+
| 0.0012 | 0.007 | 7 | 0.4171 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
66 |
+
| 0.0038 | 0.008 | 8 | 0.4370 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
67 |
+
| 0.0049 | 0.009 | 9 | 0.4496 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
68 |
+
| 0.0011 | 0.01 | 10 | 0.4553 | 0.9691 | 0.94 | 0.94 | 1.0 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- PEFT 0.13.0
|
74 |
+
- Transformers 4.45.2
|
75 |
+
- Pytorch 2.4.1+cu121
|
76 |
+
- Datasets 3.0.1
|
77 |
+
- Tokenizers 0.20.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bert-base-uncased",
|
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": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"classifier",
|
19 |
+
"score"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 8,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"bert.encoder.layer.0.attention.self.value",
|
27 |
+
"bert.encoder.layer.0.intermediate.dense",
|
28 |
+
"bert.encoder.layer.0.attention.self.query",
|
29 |
+
"bert.encoder.layer.0.attention.self.key"
|
30 |
+
],
|
31 |
+
"task_type": "SEQ_CLS",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abb5246222eccf2da20a684795e41d5ce7a9c48b8eb617ffe24d87a8d4a25f75
|
3 |
+
size 277808
|
runs/Oct08_10-45-38_f1da90e0ef55/events.out.tfevents.1728384344.f1da90e0ef55.4879.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36ae0dd6b315b8c0b72f3ce59d39c973ab2d1855bf5e89c000ba7732db2f85ea
|
3 |
+
size 12046
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9b782b02e483596cc6cea4c0ac27c592955fc05b9ecf1b1e71aa698c8f93133
|
3 |
+
size 5176
|