End of training
Browse files- .ipynb_checkpoints/config-checkpoint.json +36 -0
- README.md +73 -0
- config.json +36 -0
- model.safetensors +3 -0
- runs/Feb25_00-31-42_default/events.out.tfevents.1708821112.default.93.0 +3 -0
- training_args.bin +3 -0
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-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": "positive",
|
13 |
+
"1": "negative",
|
14 |
+
"2": "neutral"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": false,
|
32 |
+
"tie_weights_": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.37.2",
|
35 |
+
"vocab_size": 119547
|
36 |
+
}
|
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-multilingual-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: results
|
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 |
+
# results
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.8936
|
24 |
+
- Accuracy: 0.7225
|
25 |
+
- Precision: 0.6865
|
26 |
+
- Recall: 0.6703
|
27 |
+
- F1: 0.6739
|
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: 32
|
48 |
+
- eval_batch_size: 32
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 2432
|
53 |
+
- num_epochs: 999
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
59 |
+
| 0.6207 | 1.0 | 381 | 0.7457 | 0.6721 | 0.6294 | 0.6066 | 0.6065 |
|
60 |
+
| 1.3113 | 2.0 | 762 | 0.6512 | 0.7136 | 0.6835 | 0.6864 | 0.6807 |
|
61 |
+
| 1.3484 | 3.0 | 1143 | 0.6286 | 0.7149 | 0.6785 | 0.6855 | 0.6799 |
|
62 |
+
| 0.4232 | 4.0 | 1524 | 0.6430 | 0.7346 | 0.6947 | 0.6919 | 0.6931 |
|
63 |
+
| 0.4329 | 5.0 | 1905 | 0.6763 | 0.7330 | 0.6920 | 0.6807 | 0.6846 |
|
64 |
+
| 0.7608 | 6.0 | 2286 | 0.8338 | 0.7169 | 0.6925 | 0.6424 | 0.6413 |
|
65 |
+
| 0.0333 | 7.0 | 2667 | 0.8936 | 0.7225 | 0.6865 | 0.6703 | 0.6739 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.37.2
|
71 |
+
- Pytorch 2.1.0+cu121
|
72 |
+
- Datasets 2.17.1
|
73 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-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": "positive",
|
13 |
+
"1": "negative",
|
14 |
+
"2": "neutral"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": false,
|
32 |
+
"tie_weights_": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.37.2",
|
35 |
+
"vocab_size": 119547
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc34867f7627a7fd45738c9df6637600c480d45555e5f1c50301445ade1084d8
|
3 |
+
size 541320452
|
runs/Feb25_00-31-42_default/events.out.tfevents.1708821112.default.93.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1c3b8bf2fa082ed02eddd7e3a9318b812853136294a661b397a7d1a01111904
|
3 |
+
size 426831
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d4b53add5d145b3330918bb4a4905dede303e437ba7712dfdd3d5d8b5a7f2bc
|
3 |
+
size 4728
|