nguyenanh2803
commited on
Commit
•
b26c658
1
Parent(s):
5a6ba40
End of training
Browse files- README.md +3 -32
- config.json +1 -1
- special_tokens_map.json +42 -6
- tokenizer_config.json +7 -0
README.md
CHANGED
@@ -1,10 +1,8 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- accuracy
|
8 |
model-index:
|
9 |
- name: absa-train-service
|
10 |
results: []
|
@@ -13,18 +11,9 @@ model-index:
|
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721529936.8383145/runs/otcaa3ob)
|
17 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721530519.4932458/runs/6euwf05s)
|
18 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721530820.3853943/runs/fdeie61y)
|
19 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721531172.9125576/runs/jccg02qd)
|
20 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721531509.736016/runs/lsogkzq6)
|
21 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721532378.9611094/runs/kytk3wpn)
|
22 |
# absa-train-service
|
23 |
|
24 |
-
This model is a fine-tuned version of [
|
25 |
-
It achieves the following results on the evaluation set:
|
26 |
-
- Loss: 1.0968
|
27 |
-
- Accuracy: 0.699
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -50,25 +39,7 @@ The following hyperparameters were used during training:
|
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
- lr_scheduler_warmup_steps: 500
|
53 |
-
- num_epochs:
|
54 |
-
|
55 |
-
### Training results
|
56 |
-
|
57 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
58 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
59 |
-
| 2.2845 | 1.0 | 375 | 2.2437 | 0.268 |
|
60 |
-
| 2.0419 | 2.0 | 750 | 2.0310 | 0.491 |
|
61 |
-
| 1.7634 | 3.0 | 1125 | 1.8072 | 0.439 |
|
62 |
-
| 1.5688 | 4.0 | 1500 | 1.5605 | 0.634 |
|
63 |
-
| 1.4397 | 5.0 | 1875 | 1.4126 | 0.621 |
|
64 |
-
| 1.3734 | 6.0 | 2250 | 1.3115 | 0.662 |
|
65 |
-
| 1.3016 | 7.0 | 2625 | 1.2222 | 0.692 |
|
66 |
-
| 1.2229 | 8.0 | 3000 | 1.1733 | 0.679 |
|
67 |
-
| 1.2435 | 9.0 | 3375 | 1.1515 | 0.676 |
|
68 |
-
| 1.2069 | 10.0 | 3750 | 1.1158 | 0.697 |
|
69 |
-
| 1.2243 | 11.0 | 4125 | 1.1092 | 0.696 |
|
70 |
-
| 1.167 | 12.0 | 4500 | 1.0968 | 0.699 |
|
71 |
-
|
72 |
|
73 |
### Framework versions
|
74 |
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: nguyenanh2803/absa-train-service
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: absa-train-service
|
8 |
results: []
|
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
# absa-train-service
|
15 |
|
16 |
+
This model is a fine-tuned version of [nguyenanh2803/absa-train-service](https://huggingface.co/nguyenanh2803/absa-train-service) on the None dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
- lr_scheduler_warmup_steps: 500
|
42 |
+
- num_epochs: 8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
### Framework versions
|
45 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"XLMRobertaForSequenceClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "nguyenanh2803/absa-train-service",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForSequenceClassification"
|
5 |
],
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,25 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
@@ -9,7 +27,25 @@
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
-
"pad_token":
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
tokenizer_config.json
CHANGED
@@ -46,9 +46,16 @@
|
|
46 |
"cls_token": "<s>",
|
47 |
"eos_token": "</s>",
|
48 |
"mask_token": "<mask>",
|
|
|
49 |
"model_max_length": 512,
|
|
|
50 |
"pad_token": "<pad>",
|
|
|
|
|
51 |
"sep_token": "</s>",
|
|
|
52 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
53 |
"unk_token": "<unk>"
|
54 |
}
|
|
|
46 |
"cls_token": "<s>",
|
47 |
"eos_token": "</s>",
|
48 |
"mask_token": "<mask>",
|
49 |
+
"max_length": 512,
|
50 |
"model_max_length": 512,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
"pad_token": "<pad>",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
"sep_token": "</s>",
|
56 |
+
"stride": 0,
|
57 |
"tokenizer_class": "XLMRobertaTokenizer",
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "longest_first",
|
60 |
"unk_token": "<unk>"
|
61 |
}
|