End of training
Browse files- README.md +65 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +28 -0
- model.safetensors +3 -0
- runs/Apr25_15-41-22_aies-gpu-a30/events.out.tfevents.1714034482.aies-gpu-a30.45991.0 +3 -0
- runs/Apr25_15-49-00_aies-gpu-a30/events.out.tfevents.1714034941.aies-gpu-a30.45991.1 +3 -0
- runs/Apr25_16-01-00_aies-gpu-a30/events.out.tfevents.1714035660.aies-gpu-a30.45991.2 +3 -0
- runs/Apr25_16-02-21_aies-gpu-a30/events.out.tfevents.1714035742.aies-gpu-a30.47117.0 +3 -0
- runs/Apr25_16-03-10_aies-gpu-a30/events.out.tfevents.1714035791.aies-gpu-a30.47117.1 +3 -0
- runs/Apr25_16-04-28_aies-gpu-a30/events.out.tfevents.1714035871.aies-gpu-a30.47324.0 +3 -0
- runs/Apr25_16-04-28_aies-gpu-a30/events.out.tfevents.1714036411.aies-gpu-a30.47324.1 +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vinai/phobert-base-v2
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: token-classification-llmlingua2-phobert-bctn-2308_sample-10_epoch_best_data
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# token-classification-llmlingua2-phobert-bctn-2308_sample-10_epoch_best_data
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.3044
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 1e-05
|
37 |
+
- train_batch_size: 32
|
38 |
+
- eval_batch_size: 32
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 10
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| No log | 1.0 | 58 | 0.3799 |
|
49 |
+
| No log | 2.0 | 116 | 0.3286 |
|
50 |
+
| No log | 3.0 | 174 | 0.3129 |
|
51 |
+
| No log | 4.0 | 232 | 0.3105 |
|
52 |
+
| No log | 5.0 | 290 | 0.3104 |
|
53 |
+
| No log | 6.0 | 348 | 0.3064 |
|
54 |
+
| No log | 7.0 | 406 | 0.3045 |
|
55 |
+
| No log | 8.0 | 464 | 0.3049 |
|
56 |
+
| 0.3309 | 9.0 | 522 | 0.3044 |
|
57 |
+
| 0.3309 | 10.0 | 580 | 0.3054 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.39.0.dev0
|
63 |
+
- Pytorch 2.2.1+cu118
|
64 |
+
- Datasets 2.18.0
|
65 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 64000
|
3 |
+
}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 258,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"tokenizer_class": "PhobertTokenizer",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.39.0.dev0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 64001
|
28 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4db8623cfeeca4d4386415a4f6b40a68bf938f27db1165e532a23984ed7fe150
|
3 |
+
size 537660792
|
runs/Apr25_15-41-22_aies-gpu-a30/events.out.tfevents.1714034482.aies-gpu-a30.45991.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f23ac302620027398ab2c67a12892908a529c6e8e5334010c7befddbd6b9ec5
|
3 |
+
size 5014
|
runs/Apr25_15-49-00_aies-gpu-a30/events.out.tfevents.1714034941.aies-gpu-a30.45991.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e9af18398c17ad2ebf7c7e1120ed7b86c7025ee7ff2c698f045f640a87eea02
|
3 |
+
size 5014
|
runs/Apr25_16-01-00_aies-gpu-a30/events.out.tfevents.1714035660.aies-gpu-a30.45991.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e27c59b3794c01b7bda906f5a9363dfcd00b800a445330be987493d06fd9006
|
3 |
+
size 5014
|
runs/Apr25_16-02-21_aies-gpu-a30/events.out.tfevents.1714035742.aies-gpu-a30.47117.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65275de44e8db1e1ed4b4e38c329bb3a282f2507c0d04a7087fd1c1c088d41b5
|
3 |
+
size 5014
|
runs/Apr25_16-03-10_aies-gpu-a30/events.out.tfevents.1714035791.aies-gpu-a30.47117.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:247229d6f7dec8bdbacb448569fd30a415f14c9c72ab4c7858a2eaa90792df33
|
3 |
+
size 5014
|
runs/Apr25_16-04-28_aies-gpu-a30/events.out.tfevents.1714035871.aies-gpu-a30.47324.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:046775ed91b8c2a5a98069a7a216bd1e56352e9e0236364eb59de031ab2ae236
|
3 |
+
size 8279
|
runs/Apr25_16-04-28_aies-gpu-a30/events.out.tfevents.1714036411.aies-gpu-a30.47324.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3032d995f5165455241a5ef1ccc587e16a99d80a7c9b6acf60408ce1f38608b
|
3 |
+
size 359
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "PhobertTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22984602c0f565fe96e679e9489040570f5d8081ab852e6f391ee00940267ef2
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|