End of training
Browse files- README.md +46 -0
- config.json +35 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: tmp_trainer
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# tmp_trainer
|
13 |
+
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
+
|
16 |
+
## Model description
|
17 |
+
|
18 |
+
More information needed
|
19 |
+
|
20 |
+
## Intended uses & limitations
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Training and evaluation data
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
### Training hyperparameters
|
31 |
+
|
32 |
+
The following hyperparameters were used during training:
|
33 |
+
- learning_rate: 5e-05
|
34 |
+
- train_batch_size: 16
|
35 |
+
- eval_batch_size: 16
|
36 |
+
- seed: 42
|
37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
+
- lr_scheduler_type: linear
|
39 |
+
- num_epochs: 3.0
|
40 |
+
|
41 |
+
### Framework versions
|
42 |
+
|
43 |
+
- Transformers 4.35.2
|
44 |
+
- Pytorch 2.0.0
|
45 |
+
- Datasets 2.1.0
|
46 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "model_v2",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4096,
|
12 |
+
"layer_norm_eps": 1e-07,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"max_relative_positions": -1,
|
15 |
+
"model_type": "deberta-v2",
|
16 |
+
"norm_rel_ebd": "layer_norm",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_dropout": 0,
|
21 |
+
"pooler_hidden_act": "gelu",
|
22 |
+
"pooler_hidden_size": 1024,
|
23 |
+
"pos_att_type": [
|
24 |
+
"p2c",
|
25 |
+
"c2p"
|
26 |
+
],
|
27 |
+
"position_biased_input": false,
|
28 |
+
"position_buckets": 256,
|
29 |
+
"relative_attention": true,
|
30 |
+
"share_att_key": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.35.2",
|
33 |
+
"type_vocab_size": 0,
|
34 |
+
"vocab_size": 128100
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bfc6a9c4f6ee82ed1eae0c5d4f312f59256d70852e48a8825d8c8e9d406f992
|
3 |
+
size 1740300340
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2caa8fc5811d70e93c071f0dfbd0e7e8f725c11543af59809598b25fdef47324
|
3 |
+
size 4155
|