Training in progress epoch 0
Browse files- README.md +57 -0
- config.json +33 -0
- logs/train/events.out.tfevents.1667996812.ca4928603c5d.106.0.v2 +3 -0
- logs/train/events.out.tfevents.1667997190.ca4928603c5d.106.1.v2 +3 -0
- logs/train/events.out.tfevents.1667997275.ca4928603c5d.106.2.v2 +3 -0
- logs/validation/events.out.tfevents.1668005393.ca4928603c5d.106.3.v2 +3 -0
- special_tokens_map.json +15 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: DavidNo/albert-xxlarge-v2-finetuned-squadv2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# DavidNo/albert-xxlarge-v2-finetuned-squadv2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [albert-xxlarge-v2](https://huggingface.co/albert-xxlarge-v2) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 1.0842
|
18 |
+
- Train End Logits Accuracy: 0.6032
|
19 |
+
- Train Start Logits Accuracy: 0.5767
|
20 |
+
- Validation Loss: 1.1372
|
21 |
+
- Validation End Logits Accuracy: 0.5166
|
22 |
+
- Validation Start Logits Accuracy: 0.5058
|
23 |
+
- Epoch: 0
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16494, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
43 |
+
- training_precision: float32
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|
48 |
+
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
|
49 |
+
| 1.0842 | 0.6032 | 0.5767 | 1.1372 | 0.5166 | 0.5058 | 0 |
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.24.0
|
55 |
+
- TensorFlow 2.9.2
|
56 |
+
- Datasets 2.6.1
|
57 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-xxlarge-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 4096,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"inner_group_num": 1,
|
18 |
+
"intermediate_size": 16384,
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"layers_to_keep": [],
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "albert",
|
23 |
+
"net_structure_type": 0,
|
24 |
+
"num_attention_heads": 64,
|
25 |
+
"num_hidden_groups": 1,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"num_memory_blocks": 0,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"transformers_version": "4.24.0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"vocab_size": 30000
|
33 |
+
}
|
logs/train/events.out.tfevents.1667996812.ca4928603c5d.106.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1f0ec29949b5fab6ad0adc189ed4532ab504b350b71b6230553259b34e91f35
|
3 |
+
size 1696890
|
logs/train/events.out.tfevents.1667997190.ca4928603c5d.106.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcee345e72d70e4cd68da6c377dfe0a21169544fa78f0b916dbc47547ee92a81
|
3 |
+
size 1696890
|
logs/train/events.out.tfevents.1667997275.ca4928603c5d.106.2.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ba274e69a1780636ec189c9ae0376a231e462f608184394b5108a8ff032b4be
|
3 |
+
size 1717633
|
logs/validation/events.out.tfevents.1668005393.ca4928603c5d.106.3.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53d1f24300c5283717c55ed34d13d426a8e11e9ac2ec290d753f8132ad3bfaca
|
3 |
+
size 566
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:654fbf531099fd08211b2b439efdb6c12e6e1a478b24fe43a6826964ed3540ed
|
3 |
+
size 823329496
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"keep_accents": false,
|
7 |
+
"mask_token": {
|
8 |
+
"__type": "AddedToken",
|
9 |
+
"content": "[MASK]",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"model_max_length": 512,
|
16 |
+
"name_or_path": "albert-xxlarge-v2",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"remove_space": true,
|
19 |
+
"sep_token": "[SEP]",
|
20 |
+
"special_tokens_map_file": null,
|
21 |
+
"tokenizer_class": "AlbertTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|