mhr2004/roberta-base-ppaverb-5000-1e-06-8
Browse files- README.md +73 -0
- config.json +28 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: roberta-base-ppaverb-5000-1e-06-8
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
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 |
+
# roberta-base-ppaverb-5000-1e-06-8
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6899
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-06
|
38 |
+
- train_batch_size: 32
|
39 |
+
- eval_batch_size: 1024
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 30
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 157 | 0.6937 |
|
50 |
+
| 0.6962 | 2.0 | 314 | 0.6931 |
|
51 |
+
| 0.6934 | 3.0 | 471 | 0.6931 |
|
52 |
+
| 0.6934 | 4.0 | 628 | 0.6929 |
|
53 |
+
| 0.6934 | 5.0 | 785 | 0.6927 |
|
54 |
+
| 0.693 | 6.0 | 942 | 0.6926 |
|
55 |
+
| 0.6933 | 7.0 | 1099 | 0.6924 |
|
56 |
+
| 0.692 | 8.0 | 1256 | 0.6920 |
|
57 |
+
| 0.6911 | 9.0 | 1413 | 0.6918 |
|
58 |
+
| 0.6911 | 10.0 | 1570 | 0.6914 |
|
59 |
+
| 0.6907 | 11.0 | 1727 | 0.6909 |
|
60 |
+
| 0.6888 | 12.0 | 1884 | 0.6902 |
|
61 |
+
| 0.6858 | 13.0 | 2041 | 0.6896 |
|
62 |
+
| 0.6858 | 14.0 | 2198 | 0.6891 |
|
63 |
+
| 0.685 | 15.0 | 2355 | 0.6892 |
|
64 |
+
| 0.6794 | 16.0 | 2512 | 0.6892 |
|
65 |
+
| 0.6779 | 17.0 | 2669 | 0.6899 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.41.1
|
71 |
+
- Pytorch 2.3.0+cu121
|
72 |
+
- Datasets 2.19.1
|
73 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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": 514,
|
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 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.41.1",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef38eb0a786e1f6a9765f61d61d6fdb924a18723ca0e6f72b7a15e3fae577aa7
|
3 |
+
size 498612824
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2bab5fa3c7597435e66ee95a31db2ce69e25b8e7742a9b585d13b39600cdd05
|
3 |
+
size 5112
|