product
#1
by
MadhuriD
- opened
- README.md +0 -58
- config.json +0 -31
- model.safetensors +0 -3
- training_args.bin +0 -3
README.md
DELETED
@@ -1,58 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: distilbert-base-uncased
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
model-index:
|
7 |
-
- name: Product_select
|
8 |
-
results: []
|
9 |
-
---
|
10 |
-
|
11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
-
should probably proofread and complete it, then remove this comment. -->
|
13 |
-
|
14 |
-
# Product_select
|
15 |
-
|
16 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.8831
|
19 |
-
|
20 |
-
## Model description
|
21 |
-
|
22 |
-
More information needed
|
23 |
-
|
24 |
-
## Intended uses & limitations
|
25 |
-
|
26 |
-
More information needed
|
27 |
-
|
28 |
-
## Training and evaluation data
|
29 |
-
|
30 |
-
More information needed
|
31 |
-
|
32 |
-
## Training procedure
|
33 |
-
|
34 |
-
### Training hyperparameters
|
35 |
-
|
36 |
-
The following hyperparameters were used during training:
|
37 |
-
- learning_rate: 5e-05
|
38 |
-
- train_batch_size: 8
|
39 |
-
- eval_batch_size: 8
|
40 |
-
- seed: 42
|
41 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
-
- lr_scheduler_type: linear
|
43 |
-
- lr_scheduler_warmup_steps: 500
|
44 |
-
- num_epochs: 3
|
45 |
-
|
46 |
-
### Training results
|
47 |
-
|
48 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 0.9064 | 2.0 | 10 | 0.8831 |
|
51 |
-
|
52 |
-
|
53 |
-
### Framework versions
|
54 |
-
|
55 |
-
- Transformers 4.42.4
|
56 |
-
- Pytorch 2.3.1+cu121
|
57 |
-
- Datasets 2.20.0
|
58 |
-
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
@@ -1,31 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
-
"architectures": [
|
5 |
-
"DistilBertForSequenceClassification"
|
6 |
-
],
|
7 |
-
"attention_dropout": 0.1,
|
8 |
-
"dim": 768,
|
9 |
-
"dropout": 0.1,
|
10 |
-
"hidden_dim": 3072,
|
11 |
-
"id2label": {
|
12 |
-
"0": "LABEL_0"
|
13 |
-
},
|
14 |
-
"initializer_range": 0.02,
|
15 |
-
"label2id": {
|
16 |
-
"LABEL_0": 0
|
17 |
-
},
|
18 |
-
"max_position_embeddings": 512,
|
19 |
-
"model_type": "distilbert",
|
20 |
-
"n_heads": 12,
|
21 |
-
"n_layers": 6,
|
22 |
-
"pad_token_id": 0,
|
23 |
-
"problem_type": "regression",
|
24 |
-
"qa_dropout": 0.1,
|
25 |
-
"seq_classif_dropout": 0.2,
|
26 |
-
"sinusoidal_pos_embds": false,
|
27 |
-
"tie_weights_": true,
|
28 |
-
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.42.4",
|
30 |
-
"vocab_size": 30522
|
31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:eb883433efdff81c7b673dc94d31061841745981ba7276785c7f6748c01fbb72
|
3 |
-
size 267829484
|
|
|
|
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7f83e1ba8f0b2930e27e3f601bcd60e407b764744f105a391d2e1000af3b6dcb
|
3 |
-
size 5048
|
|
|
|
|
|
|
|