Training in progress epoch 0
Browse files- README.md +55 -0
- config.json +52 -0
- logs/train/events.out.tfevents.1701161161.129-146-96-115.897155.0.v2 +3 -0
- logs/validation/events.out.tfevents.1701162564.129-146-96-115.897155.1.v2 +3 -0
- special_tokens_map.json +19 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +93 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlnet-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: svenbl80/xlnet-base-cased-finetuned-mnli
|
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 |
+
# svenbl80/xlnet-base-cased-finetuned-mnli
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.4875
|
19 |
+
- Validation Loss: 0.3953
|
20 |
+
- Train Accuracy: 0.8520
|
21 |
+
- Epoch: 0
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 736290, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
+
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 0.4875 | 0.3953 | 0.8520 | 0 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.35.2
|
53 |
+
- TensorFlow 2.11.0
|
54 |
+
- Datasets 2.15.0
|
55 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlnet-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"XLNetForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attn_type": "bi",
|
7 |
+
"bi_data": false,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"clamp_len": -1,
|
10 |
+
"d_head": 64,
|
11 |
+
"d_inner": 3072,
|
12 |
+
"d_model": 768,
|
13 |
+
"dropout": 0.1,
|
14 |
+
"end_n_top": 5,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"ff_activation": "gelu",
|
17 |
+
"id2label": {
|
18 |
+
"0": "entailment",
|
19 |
+
"1": "neutral",
|
20 |
+
"2": "contradiction"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"contradiction": 2,
|
25 |
+
"entailment": 0,
|
26 |
+
"neutral": 1
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"mem_len": null,
|
30 |
+
"model_type": "xlnet",
|
31 |
+
"n_head": 12,
|
32 |
+
"n_layer": 12,
|
33 |
+
"pad_token_id": 5,
|
34 |
+
"reuse_len": null,
|
35 |
+
"same_length": false,
|
36 |
+
"start_n_top": 5,
|
37 |
+
"summary_activation": "tanh",
|
38 |
+
"summary_last_dropout": 0.1,
|
39 |
+
"summary_type": "last",
|
40 |
+
"summary_use_proj": true,
|
41 |
+
"task_specific_params": {
|
42 |
+
"text-generation": {
|
43 |
+
"do_sample": true,
|
44 |
+
"max_length": 250
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"transformers_version": "4.35.2",
|
48 |
+
"untie_r": true,
|
49 |
+
"use_mems_eval": true,
|
50 |
+
"use_mems_train": false,
|
51 |
+
"vocab_size": 32000
|
52 |
+
}
|
logs/train/events.out.tfevents.1701161161.129-146-96-115.897155.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f639ad36bce9349568ce636d94d9ba74d998596a337194215254efa99f34b976
|
3 |
+
size 3546448
|
logs/validation/events.out.tfevents.1701162564.129-146-96-115.897155.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fdcc2295fc0588c36a8d39cc33fdba3318cff2ce8dcaf3f50a5e5db076c1487
|
3 |
+
size 195
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<eop>",
|
4 |
+
"<eod>"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<cls>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "<sep>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cac0f5d3e696c652f20e0eec9d54bc639508f25f11625fa1a22be282396512ea
|
3 |
+
size 469433904
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<cls>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<sep>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<pad>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "<mask>",
|
53 |
+
"lstrip": true,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<eod>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<eop>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"additional_special_tokens": [
|
77 |
+
"<eop>",
|
78 |
+
"<eod>"
|
79 |
+
],
|
80 |
+
"bos_token": "<s>",
|
81 |
+
"clean_up_tokenization_spaces": true,
|
82 |
+
"cls_token": "<cls>",
|
83 |
+
"do_lower_case": false,
|
84 |
+
"eos_token": "</s>",
|
85 |
+
"keep_accents": false,
|
86 |
+
"mask_token": "<mask>",
|
87 |
+
"model_max_length": 1000000000000000019884624838656,
|
88 |
+
"pad_token": "<pad>",
|
89 |
+
"remove_space": true,
|
90 |
+
"sep_token": "<sep>",
|
91 |
+
"tokenizer_class": "XLNetTokenizer",
|
92 |
+
"unk_token": "<unk>"
|
93 |
+
}
|