OctavianB/BERT_emotion_entailment
Browse files- README.md +18 -12
- config.json +15 -35
- model.safetensors +2 -2
- runs/Jan25_07-41-14_155994e85fd6/events.out.tfevents.1706168477.155994e85fd6.2012.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,10 +1,13 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: test_trainer
|
10 |
results: []
|
@@ -15,10 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# test_trainer
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,20 +49,20 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs: 3
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
-
| Training Loss | Epoch | Step
|
51 |
-
|
52 |
-
|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
-
- Transformers 4.
|
60 |
- Pytorch 2.1.0+cu121
|
61 |
- Datasets 2.16.1
|
62 |
-
- Tokenizers 0.15.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
model-index:
|
12 |
- name: test_trainer
|
13 |
results: []
|
|
|
18 |
|
19 |
# test_trainer
|
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: 0.5486
|
24 |
+
- Accuracy: 0.9374
|
25 |
+
- F1: 0.5984
|
26 |
+
- Precision: 0.7067
|
27 |
+
- Recall: 0.5189
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 3
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 0.6604 | 1.0 | 9009 | 0.6454 | 0.9258 | 0.3847 | 0.7537 | 0.2583 |
|
59 |
+
| 0.5947 | 2.0 | 18018 | 0.4696 | 0.9356 | 0.6004 | 0.6779 | 0.5387 |
|
60 |
+
| 0.5444 | 3.0 | 27027 | 0.5486 | 0.9374 | 0.5984 | 0.7067 | 0.5189 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
+
- Transformers 4.37.1
|
66 |
- Pytorch 2.1.0+cu121
|
67 |
- Datasets 2.16.1
|
68 |
+
- Tokenizers 0.15.1
|
config.json
CHANGED
@@ -1,45 +1,25 @@
|
|
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": "LABEL_0",
|
14 |
-
"1": "LABEL_1",
|
15 |
-
"2": "LABEL_2",
|
16 |
-
"3": "LABEL_3",
|
17 |
-
"4": "LABEL_4",
|
18 |
-
"5": "LABEL_5",
|
19 |
-
"6": "LABEL_6"
|
20 |
-
},
|
21 |
"initializer_range": 0.02,
|
22 |
-
"intermediate_size": 3072,
|
23 |
-
"label2id": {
|
24 |
-
"LABEL_0": 0,
|
25 |
-
"LABEL_1": 1,
|
26 |
-
"LABEL_2": 2,
|
27 |
-
"LABEL_3": 3,
|
28 |
-
"LABEL_4": 4,
|
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 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
"pad_token_id": 0,
|
|
|
17 |
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.37.1",
|
|
|
|
|
24 |
"vocab_size": 30522
|
25 |
}
|
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 sha256:8d14dca093553a7648b5c03b492dd3b93551f1a068ddaca4b0986338817dce82
|
3 |
+
size 267832560
|
runs/Jan25_07-41-14_155994e85fd6/events.out.tfevents.1706168477.155994e85fd6.2012.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6847c17b912871c73d5a507b0083d6e7f1e60c4b3a55d1fd43aa44dcf9322800
|
3 |
+
size 14556
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378e0e36c069bc242e0e3be19ce262d4bb1595e70a2056ec87a90793312e3f88
|
3 |
size 4664
|