SimoneJLaudani
commited on
Commit
•
2e01ae9
1
Parent(s):
e64b055
End of training
Browse files- README.md +29 -14
- config.json +15 -17
- model.safetensors +2 -2
- runs/Apr21_10-40-37_7c6a6620afc9/events.out.tfevents.1713696045.7c6a6620afc9.602.0 +3 -0
- runs/Apr21_10-43-19_7c6a6620afc9/events.out.tfevents.1713696203.7c6a6620afc9.602.1 +3 -0
- runs/Apr21_11-03-28_7c6a6620afc9/events.out.tfevents.1713697412.7c6a6620afc9.602.2 +3 -0
- tokenizer_config.json +4 -2
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# trainer6
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -43,21 +43,36 @@ More information needed
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
-
- learning_rate:
|
47 |
-
- train_batch_size:
|
48 |
-
- eval_batch_size:
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
|
54 |
### Training results
|
55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
-
- Transformers 4.
|
61 |
- Pytorch 2.2.1+cu121
|
62 |
-
- Datasets 2.
|
63 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# trainer6
|
20 |
|
21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.8990
|
24 |
+
- Precision: 0.8531
|
25 |
+
- Recall: 0.8519
|
26 |
+
- F1: 0.8521
|
27 |
+
- Accuracy: 0.8519
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 64
|
48 |
+
- eval_batch_size: 64
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 30
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 1.0015 | 2.2222 | 100 | 0.5893 | 0.8219 | 0.8183 | 0.8179 | 0.8183 |
|
59 |
+
| 0.1719 | 4.4444 | 200 | 0.6665 | 0.8264 | 0.8201 | 0.8209 | 0.8201 |
|
60 |
+
| 0.0505 | 6.6667 | 300 | 0.7009 | 0.8474 | 0.8430 | 0.8439 | 0.8430 |
|
61 |
+
| 0.0182 | 8.8889 | 400 | 0.7909 | 0.8481 | 0.8413 | 0.8425 | 0.8413 |
|
62 |
+
| 0.0124 | 11.1111 | 500 | 0.8725 | 0.8401 | 0.8377 | 0.8377 | 0.8377 |
|
63 |
+
| 0.0075 | 13.3333 | 600 | 0.8820 | 0.8469 | 0.8430 | 0.8426 | 0.8430 |
|
64 |
+
| 0.0081 | 15.5556 | 700 | 0.8637 | 0.8396 | 0.8360 | 0.8362 | 0.8360 |
|
65 |
+
| 0.0051 | 17.7778 | 800 | 0.8981 | 0.8471 | 0.8448 | 0.8447 | 0.8448 |
|
66 |
+
| 0.0047 | 20.0 | 900 | 0.8829 | 0.8549 | 0.8536 | 0.8539 | 0.8536 |
|
67 |
+
| 0.0027 | 22.2222 | 1000 | 0.8943 | 0.8522 | 0.8501 | 0.8504 | 0.8501 |
|
68 |
+
| 0.0026 | 24.4444 | 1100 | 0.8910 | 0.8531 | 0.8519 | 0.8521 | 0.8519 |
|
69 |
+
| 0.0027 | 26.6667 | 1200 | 0.8933 | 0.8532 | 0.8519 | 0.8520 | 0.8519 |
|
70 |
+
| 0.0028 | 28.8889 | 1300 | 0.8990 | 0.8531 | 0.8519 | 0.8521 | 0.8519 |
|
71 |
|
72 |
|
73 |
### Framework versions
|
74 |
|
75 |
+
- Transformers 4.40.0
|
76 |
- Pytorch 2.2.1+cu121
|
77 |
+
- Datasets 2.19.0
|
78 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "anger",
|
14 |
"1": "fear",
|
@@ -19,7 +18,6 @@
|
|
19 |
"6": "surprise"
|
20 |
},
|
21 |
"initializer_range": 0.02,
|
22 |
-
"intermediate_size": 3072,
|
23 |
"label2id": {
|
24 |
"LABEL_0": 0,
|
25 |
"LABEL_1": 1,
|
@@ -29,17 +27,17 @@
|
|
29 |
"LABEL_5": 5,
|
30 |
"LABEL_6": 6
|
31 |
},
|
32 |
-
"layer_norm_eps": 1e-12,
|
33 |
"max_position_embeddings": 512,
|
34 |
-
"model_type": "
|
35 |
-
"
|
36 |
-
"
|
37 |
"pad_token_id": 0,
|
38 |
-
"position_embedding_type": "absolute",
|
39 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
40 |
"torch_dtype": "float32",
|
41 |
-
"transformers_version": "4.
|
42 |
-
"type_vocab_size": 2,
|
43 |
-
"use_cache": true,
|
44 |
"vocab_size": 30522
|
45 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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",
|
|
|
18 |
"6": "surprise"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
|
|
21 |
"label2id": {
|
22 |
"LABEL_0": 0,
|
23 |
"LABEL_1": 1,
|
|
|
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 |
"pad_token_id": 0,
|
|
|
35 |
"problem_type": "single_label_classification",
|
36 |
+
"qa_dropout": 0.1,
|
37 |
+
"seq_classif_dropout": 0.2,
|
38 |
+
"sinusoidal_pos_embds": false,
|
39 |
+
"tie_weights_": true,
|
40 |
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.40.0",
|
|
|
|
|
42 |
"vocab_size": 30522
|
43 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a372ee7f96d4b09a0986f8203d36bd942893a1490a4b43f6c11146317b9b95
|
3 |
+
size 267847948
|
runs/Apr21_10-40-37_7c6a6620afc9/events.out.tfevents.1713696045.7c6a6620afc9.602.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3325fd606e2c2de653bcee75a97432b1654f75ee9ab6236148e6a41acb5a1e2b
|
3 |
+
size 5508
|
runs/Apr21_10-43-19_7c6a6620afc9/events.out.tfevents.1713696203.7c6a6620afc9.602.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cc47f1fbd2b1f8c3bef1a5dc873fa19eb61a449be9455fc4bafe02e11311d4f
|
3 |
+
size 14790
|
runs/Apr21_11-03-28_7c6a6620afc9/events.out.tfevents.1713697412.7c6a6620afc9.602.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25ee4d97e8ff8f7d78c8d4ddf95b46f73fe1eaeec8309579441f4290fdf4d8fc
|
3 |
+
size 14056
|
tokenizer_config.json
CHANGED
@@ -43,13 +43,15 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
|
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1bd6ec0c8864e9602f2156c5092a9b0839dcbb1f8341753f228a5da77fdab42
|
3 |
+
size 4984
|