derek-harnett
commited on
Commit
•
98aabe0
1
Parent(s):
0c583af
test push_to_hub()
Browse files- README.md +10 -17
- config.json +1 -1
- model.safetensors +1 -1
- runs/Aug02_23-02-24_c7531b552757/events.out.tfevents.1722639745.c7531b552757.174.0 +3 -0
- runs/Aug02_23-02-24_c7531b552757/events.out.tfevents.1722641252.c7531b552757.174.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +2 -2
- vocab.txt +0 -0
README.md
CHANGED
@@ -4,9 +4,6 @@ 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: movie-review-classifier
|
@@ -20,11 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
-
|
25 |
-
- Precision: 0.9131
|
26 |
-
- Recall: 0.9296
|
27 |
-
- F1: 0.9213
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -49,20 +43,19 @@ The following hyperparameters were used during training:
|
|
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 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
-
|
58 |
-
|
|
59 |
-
|
|
60 |
-
| 0.0991 | 3.0 | 2346 | 0.3105 | 0.9207 | 0.9131 | 0.9296 | 0.9213 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
-
- Transformers 4.
|
66 |
-
- Pytorch 2.3.
|
67 |
-
- Datasets 2.
|
68 |
- Tokenizers 0.19.1
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
|
|
|
|
7 |
- f1
|
8 |
model-index:
|
9 |
- name: movie-review-classifier
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2973
|
21 |
+
- F1: 0.8828
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 2
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
52 |
+
| No log | 1.0 | 63 | 0.3670 | 0.8643 |
|
53 |
+
| No log | 2.0 | 126 | 0.2973 | 0.8828 |
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.42.4
|
59 |
+
- Pytorch 2.3.1+cu121
|
60 |
+
- Datasets 2.20.0
|
61 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -20,6 +20,6 @@
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.42.4",
|
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 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c88f8f4918407c5b881a0338b3c1bb871a1866b4bd4ebb6037db3f04da85a95
|
3 |
size 267832560
|
runs/Aug02_23-02-24_c7531b552757/events.out.tfevents.1722639745.c7531b552757.174.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:295042091e822e08b2e5100d93048f49b169d72fb943f2adfd37d2ba1fe987e2
|
3 |
+
size 5730
|
runs/Aug02_23-02-24_c7531b552757/events.out.tfevents.1722641252.c7531b552757.174.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54e4564279e711a7fa9f28e437a468bc438eefa30c32d1000daf4ad0ceed2b28
|
3 |
+
size 399
|
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
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 sha256:757546e613e0a3a33dceb40f86a250d8c5b343aaa50dc610a055ea2eb1cfd5eb
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|