ashhadahsan
commited on
Commit
•
349d0a6
1
Parent(s):
312eb32
Training in progress epoch 0
Browse files- README.md +55 -0
- config.json +57 -0
- logs/train/events.out.tfevents.1692296835.470540468b49.1002.0.v2 +3 -0
- logs/validation/events.out.tfevents.1692297011.470540468b49.1002.1.v2 +3 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: ashhadahsan/amazon-theme-bert-base-finetuned
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# ashhadahsan/amazon-theme-bert-base-finetuned
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.3910
|
19 |
+
- Train Accuracy: 0.5974
|
20 |
+
- Validation Loss: 0.8022
|
21 |
+
- Validation Accuracy: 0.8008
|
22 |
+
- Epoch: 0
|
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 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
42 |
+
- training_precision: float32
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
47 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
48 |
+
| 1.3910 | 0.5974 | 0.8022 | 0.8008 | 0 |
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.31.0
|
54 |
+
- TensorFlow 2.12.0
|
55 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Ads",
|
14 |
+
"1": "Apps",
|
15 |
+
"2": "Battery",
|
16 |
+
"3": "Charging",
|
17 |
+
"4": "Delivery",
|
18 |
+
"5": "Display",
|
19 |
+
"6": "FOS",
|
20 |
+
"7": "HW",
|
21 |
+
"8": "Order",
|
22 |
+
"9": "Refurb",
|
23 |
+
"10": "SD",
|
24 |
+
"11": "Setup",
|
25 |
+
"12": "Unknown",
|
26 |
+
"13": "WiFi"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"Ads": 0,
|
32 |
+
"Apps": 1,
|
33 |
+
"Battery": 2,
|
34 |
+
"Charging": 3,
|
35 |
+
"Delivery": 4,
|
36 |
+
"Display": 5,
|
37 |
+
"FOS": 6,
|
38 |
+
"HW": 7,
|
39 |
+
"Order": 8,
|
40 |
+
"Refurb": 9,
|
41 |
+
"SD": 10,
|
42 |
+
"Setup": 11,
|
43 |
+
"Unknown": 12,
|
44 |
+
"WiFi": 13
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-12,
|
47 |
+
"max_position_embeddings": 512,
|
48 |
+
"model_type": "bert",
|
49 |
+
"num_attention_heads": 12,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"pad_token_id": 0,
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"transformers_version": "4.31.0",
|
54 |
+
"type_vocab_size": 2,
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 30522
|
57 |
+
}
|
logs/train/events.out.tfevents.1692296835.470540468b49.1002.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfcd908caec83f90f11bc0cd4b3ecf1186391c2a9ca27de3f9e54a6483e65fef
|
3 |
+
size 4190389
|
logs/validation/events.out.tfevents.1692297011.470540468b49.1002.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb7fbe2398eb1fa49ac00041cb57092f1dedef88a2f33fc5302672aa13c34a33
|
3 |
+
size 394
|
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 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:329bd7a81f3c01d5a6f2312b21094c5a62f2ea51c9dd4496b4d7532774f35413
|
3 |
+
size 438260040
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|