SimoneJLaudani
commited on
Commit
•
66a623b
1
Parent(s):
387523f
End of training
Browse files- README.md +82 -0
- config.json +44 -0
- model.safetensors +3 -0
- runs/Mar14_20-55-19_18c119a900f6/events.out.tfevents.1710449726.18c119a900f6.18759.15 +3 -0
- runs/Mar14_20-56-40_18c119a900f6/events.out.tfevents.1710449810.18c119a900f6.18759.16 +3 -0
- runs/Mar14_20-56-40_18c119a900f6/events.out.tfevents.1710453015.18c119a900f6.18759.17 +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: trainer3
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# trainer3
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0000
|
24 |
+
- Precision: 1.0
|
25 |
+
- Recall: 1.0
|
26 |
+
- F1: 1.0
|
27 |
+
- Accuracy: 1.0
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
|
58 |
+
| 0.0053 | 0.57 | 30 | 0.0010 | 1.0 | 1.0 | 1.0 | 1.0 |
|
59 |
+
| 0.0011 | 1.13 | 60 | 0.0004 | 1.0 | 1.0 | 1.0 | 1.0 |
|
60 |
+
| 0.0006 | 1.7 | 90 | 0.0003 | 1.0 | 1.0 | 1.0 | 1.0 |
|
61 |
+
| 0.0004 | 2.26 | 120 | 0.0002 | 1.0 | 1.0 | 1.0 | 1.0 |
|
62 |
+
| 0.0003 | 2.83 | 150 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
63 |
+
| 0.0002 | 3.4 | 180 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
64 |
+
| 0.0002 | 3.96 | 210 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
65 |
+
| 0.0002 | 4.53 | 240 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
66 |
+
| 0.0001 | 5.09 | 270 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
67 |
+
| 0.0001 | 5.66 | 300 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
68 |
+
| 0.0001 | 6.23 | 330 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
69 |
+
| 0.0001 | 6.79 | 360 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 |
|
70 |
+
| 0.0001 | 7.36 | 390 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
|
71 |
+
| 0.0001 | 7.92 | 420 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
|
72 |
+
| 0.0001 | 8.49 | 450 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
|
73 |
+
| 0.0001 | 9.06 | 480 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
|
74 |
+
| 0.0001 | 9.62 | 510 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.38.2
|
80 |
+
- Pytorch 2.2.1+cu121
|
81 |
+
- Datasets 2.18.0
|
82 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "anger",
|
13 |
+
"1": "fear",
|
14 |
+
"2": "joy",
|
15 |
+
"3": "love",
|
16 |
+
"4": "neutral",
|
17 |
+
"5": "sadness",
|
18 |
+
"6": "surprise"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2,
|
25 |
+
"LABEL_3": 3,
|
26 |
+
"LABEL_4": 4,
|
27 |
+
"LABEL_5": 5,
|
28 |
+
"LABEL_6": 6
|
29 |
+
},
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "distilbert",
|
32 |
+
"n_heads": 12,
|
33 |
+
"n_layers": 6,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"qa_dropout": 0.1,
|
38 |
+
"seq_classif_dropout": 0.2,
|
39 |
+
"sinusoidal_pos_embds": false,
|
40 |
+
"tie_weights_": true,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.38.2",
|
43 |
+
"vocab_size": 28996
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:679f4e90a90ac7ba59cd0739e5a1c303f01af16ee28cec1f10841739c6d4b59a
|
3 |
+
size 263160068
|
runs/Mar14_20-55-19_18c119a900f6/events.out.tfevents.1710449726.18c119a900f6.18759.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20beaba317067639890c6ab3389d1b4063004b10de147f1ad024065e92188dc4
|
3 |
+
size 4836
|
runs/Mar14_20-56-40_18c119a900f6/events.out.tfevents.1710449810.18c119a900f6.18759.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2cb64b730bfc80e9f629b247f384fa2873e31250d3d3572221f26a9ac1ac44e
|
3 |
+
size 16749
|
runs/Mar14_20-56-40_18c119a900f6/events.out.tfevents.1710453015.18c119a900f6.18759.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f55bb64f479e5280ea186104e9e3c03439b1c125dc0e314d73209da8c999b0ef
|
3 |
+
size 560
|
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 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
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:f7329b620bc727f600e8a0d41f340aa133e431f0d55f6b7ecacd1f0cfce946b1
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|