Model save
Browse files- README.md +61 -0
- config.json +50 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jul29_10-22-15_IN39402000/events.out.tfevents.1722262237.IN39402000.17436.0 +3 -0
- runs/Jul29_10-22-15_IN39402000/events.out.tfevents.1722263810.IN39402000.17436.1 +3 -0
- runs/Jul29_10-22-15_IN39402000/events.out.tfevents.1722270255.IN39402000.17436.2 +3 -0
- runs/Jul29_13-41-42_IN39402000/events.out.tfevents.1722271311.IN39402000.17436.3 +3 -0
- runs/Jul29_13-49-01_IN39402000/events.out.tfevents.1722271752.IN39402000.17436.4 +3 -0
- runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722273017.IN39402000.17436.5 +3 -0
- runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722273866.IN39402000.17436.6 +3 -0
- runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722274245.IN39402000.17436.7 +3 -0
- runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722275425.IN39402000.17436.8 +3 -0
- runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722277216.IN39402000.17436.9 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: facebook/bart-large-mnli
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: bart-large-mnli-finetuned
|
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 |
+
# bart-large-mnli-finetuned
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0000
|
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: 2e-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 |
+
- num_epochs: 5
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 0.0001 | 1.0 | 8 | 0.0000 |
|
50 |
+
| 0.0005 | 2.0 | 16 | 0.0000 |
|
51 |
+
| 0.0034 | 3.0 | 24 | 0.0000 |
|
52 |
+
| 0.0 | 4.0 | 32 | 0.0000 |
|
53 |
+
| 0.0 | 5.0 | 40 | 0.0000 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.37.2
|
59 |
+
- Pytorch 2.2.0
|
60 |
+
- Datasets 2.19.1
|
61 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large-mnli",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForSequenceClassification"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"encoder_attention_heads": 16,
|
22 |
+
"encoder_ffn_dim": 4096,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 12,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
+
"id2label": {
|
29 |
+
"0": "negativo",
|
30 |
+
"1": "positivo"
|
31 |
+
},
|
32 |
+
"init_std": 0.02,
|
33 |
+
"is_encoder_decoder": true,
|
34 |
+
"label2id": {
|
35 |
+
"negativo": 0,
|
36 |
+
"positivo": 1
|
37 |
+
},
|
38 |
+
"max_position_embeddings": 1024,
|
39 |
+
"model_type": "bart",
|
40 |
+
"normalize_before": false,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"output_past": false,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"scale_embedding": false,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.37.2",
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 50265
|
50 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ab65a04af4a04ff4f6f25f998b1fd224e3bd2e605ad1c23adbd5996efbc9b39
|
3 |
+
size 1629432864
|
runs/Jul29_10-22-15_IN39402000/events.out.tfevents.1722262237.IN39402000.17436.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c56201df947dc7982a3f411a26ea1267799e748afab5abbf322706c58cf5dd5d
|
3 |
+
size 9664
|
runs/Jul29_10-22-15_IN39402000/events.out.tfevents.1722263810.IN39402000.17436.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:020d792346c5f31cfae2957b95e1b88e37ae692102d2abc7518e21dba40b6876
|
3 |
+
size 4876
|
runs/Jul29_10-22-15_IN39402000/events.out.tfevents.1722270255.IN39402000.17436.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78caf0d7e4305e9abf165ae2f2f20fe2de08633b771f7c55349c43015d017ce3
|
3 |
+
size 4876
|
runs/Jul29_13-41-42_IN39402000/events.out.tfevents.1722271311.IN39402000.17436.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:447c3072ce0a1ea0267e1e2023ecf72b95a74eb500f68e1fe994c9f8407b6039
|
3 |
+
size 5030
|
runs/Jul29_13-49-01_IN39402000/events.out.tfevents.1722271752.IN39402000.17436.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9986d58dc6dceb581b6dd79be14c611584df88cfc9b6249c02a0906bdaa6aa1f
|
3 |
+
size 5079
|
runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722273017.IN39402000.17436.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f63a52d2b6ec4604c27fae58df707cce5beffd1bbece07f6ff02bc238740b88
|
3 |
+
size 5079
|
runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722273866.IN39402000.17436.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:772210333f438a2b6dcc579c525deac9e7e129d7c7fd2345dd16b0a0f8418ebb
|
3 |
+
size 5079
|
runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722274245.IN39402000.17436.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0455a84f69a1a9676613e32d18f4ebf86c5dedeed203f3fde388371820bcdd5
|
3 |
+
size 7373
|
runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722275425.IN39402000.17436.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eab6e15db9d1bc522a6ebaac9cc1106371b057982c418cf94091a5aa66396f2
|
3 |
+
size 7373
|
runs/Jul29_14-10-09_IN39402000/events.out.tfevents.1722277216.IN39402000.17436.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10924bdf8c0ebd2ebb9d448bfff3da45d5c05e7f78027a52c0289945770aac6d
|
3 |
+
size 354
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25d7f8a1687e7bc07b3a941ccf204dc7eeb92b332697082ad57f692e2e9ab985
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|