vasu11-distilbert-base-uncased-finetuned-resume
Browse files- README.md +70 -0
- config.json +49 -0
- model.safetensors +3 -0
- runs/Mar29_14-07-33_d12b6bcb699a/events.out.tfevents.1711721296.d12b6bcb699a.3841.0 +3 -0
- runs/Mar29_14-14-24_d12b6bcb699a/events.out.tfevents.1711721665.d12b6bcb699a.6053.0 +3 -0
- runs/Mar29_14-14-51_d12b6bcb699a/events.out.tfevents.1711721967.d12b6bcb699a.6053.1 +3 -0
- runs/Mar29_14-24-08_d12b6bcb699a/events.out.tfevents.1711722248.d12b6bcb699a.7929.0 +3 -0
- runs/Mar30_09-39-30_d12b6bcb699a/events.out.tfevents.1711791570.d12b6bcb699a.742.0 +3 -0
- runs/Mar30_10-15-11_d12b6bcb699a/events.out.tfevents.1711793711.d12b6bcb699a.7533.0 +3 -0
- runs/Mar30_10-15-11_d12b6bcb699a/events.out.tfevents.1711796858.d12b6bcb699a.7533.1 +3 -0
- runs/Mar30_12-41-30_d12b6bcb699a/events.out.tfevents.1711802490.d12b6bcb699a.362.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: distilbert-base-uncased-finetuned-resume
|
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 |
+
# distilbert-base-uncased-finetuned-resume
|
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: 0.7572
|
24 |
+
- Accuracy: 0.6121
|
25 |
+
- Precision: 0.5993
|
26 |
+
- Recall: 0.5837
|
27 |
+
- F1: 0.5817
|
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: 3e-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 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
58 |
+
| 0.961 | 1.0 | 583 | 0.7683 | 0.6508 | 0.6194 | 0.5758 | 0.5509 |
|
59 |
+
| 0.7218 | 2.0 | 1166 | 0.7392 | 0.6424 | 0.6484 | 0.5936 | 0.5577 |
|
60 |
+
| 0.6682 | 3.0 | 1749 | 0.7518 | 0.6358 | 0.5780 | 0.6620 | 0.6089 |
|
61 |
+
| 0.6262 | 4.0 | 2332 | 0.7457 | 0.6199 | 0.5959 | 0.6417 | 0.5964 |
|
62 |
+
| 0.59 | 5.0 | 2915 | 0.7572 | 0.6121 | 0.5993 | 0.5837 | 0.5817 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.35.2
|
68 |
+
- Pytorch 2.1.0+cu121
|
69 |
+
- Datasets 2.18.0
|
70 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Database_Administrator",
|
13 |
+
"1": "Front_End_Developer",
|
14 |
+
"2": "Java_Developer",
|
15 |
+
"3": "Network_Administrator",
|
16 |
+
"4": "Project_manager",
|
17 |
+
"5": "Python_Developer",
|
18 |
+
"6": "Security_Analyst",
|
19 |
+
"7": "Software_Developer",
|
20 |
+
"8": "Systems_Administrator",
|
21 |
+
"9": "Web_Developer"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"label2id": {
|
25 |
+
"Database_Administrator": 0,
|
26 |
+
"Front_End_Developer": 1,
|
27 |
+
"Java_Developer": 2,
|
28 |
+
"Network_Administrator": 3,
|
29 |
+
"Project_manager": 4,
|
30 |
+
"Python_Developer": 5,
|
31 |
+
"Security_Analyst": 6,
|
32 |
+
"Software_Developer": 7,
|
33 |
+
"Systems_Administrator": 8,
|
34 |
+
"Web_Developer": 9
|
35 |
+
},
|
36 |
+
"max_position_embeddings": 512,
|
37 |
+
"model_type": "distilbert",
|
38 |
+
"n_heads": 12,
|
39 |
+
"n_layers": 6,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"problem_type": "single_label_classification",
|
42 |
+
"qa_dropout": 0.1,
|
43 |
+
"seq_classif_dropout": 0.2,
|
44 |
+
"sinusoidal_pos_embds": false,
|
45 |
+
"tie_weights_": true,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.35.2",
|
48 |
+
"vocab_size": 30522
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3172274b1961cf7c0dfecb4250fb1545bc9e4357094550f99eaa93d2d5e7efc6
|
3 |
+
size 267857176
|
runs/Mar29_14-07-33_d12b6bcb699a/events.out.tfevents.1711721296.d12b6bcb699a.3841.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62eda58341a210bc9caf89a4d41da67e02e5dee4a377a500d0f254d3de51879c
|
3 |
+
size 4795
|
runs/Mar29_14-14-24_d12b6bcb699a/events.out.tfevents.1711721665.d12b6bcb699a.6053.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7291a3bde0517409dd7e84f60005a49e02a2987bf60565c688cf14152356b4b
|
3 |
+
size 4795
|
runs/Mar29_14-14-51_d12b6bcb699a/events.out.tfevents.1711721967.d12b6bcb699a.6053.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd4d012394bfb61c61b633a806a83b16a69acb571591af231aa7710cd318487d
|
3 |
+
size 9504
|
runs/Mar29_14-24-08_d12b6bcb699a/events.out.tfevents.1711722248.d12b6bcb699a.7929.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71559d2d57edfb4f1b1239a25fe90260cfc80350645453fae0642d9643db63d9
|
3 |
+
size 4184
|
runs/Mar30_09-39-30_d12b6bcb699a/events.out.tfevents.1711791570.d12b6bcb699a.742.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62aa1913ca679df84125f7824b3bc8c70b883a4bb29b3ebe1b36aab8ed405690
|
3 |
+
size 6434
|
runs/Mar30_10-15-11_d12b6bcb699a/events.out.tfevents.1711793711.d12b6bcb699a.7533.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1560c276b0509a55d5619f4525703fc9bf14860327bb191b0ca22aea28684972
|
3 |
+
size 7287
|
runs/Mar30_10-15-11_d12b6bcb699a/events.out.tfevents.1711796858.d12b6bcb699a.7533.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c2be810fdf1f3b3b4615a8aa251cdf66d5729a44fc045fb1278289e78d60e77
|
3 |
+
size 359
|
runs/Mar30_12-41-30_d12b6bcb699a/events.out.tfevents.1711802490.d12b6bcb699a.362.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3fcd14a14f04bbcd69827665d06bc8e67fae60085a6e209e2ce7b5e71fe8be3
|
3 |
+
size 8291
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41aea1d07a2ed31a45eec954d50de410983b96afb0af63aa02b142a40ffeb242
|
3 |
+
size 4600
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|