Wonder-Griffin
commited on
Commit
•
1263c13
1
Parent(s):
6e5101d
Model save
Browse files- README.md +45 -1
- config.json +33 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,47 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: TraXL
|
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 |
+
# TraXL
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
16 |
+
|
17 |
+
## Model description
|
18 |
+
|
19 |
+
More information needed
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Training and evaluation data
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training procedure
|
30 |
+
|
31 |
+
### Training hyperparameters
|
32 |
+
|
33 |
+
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 5e-05
|
35 |
+
- train_batch_size: 8
|
36 |
+
- eval_batch_size: 8
|
37 |
+
- seed: 42
|
38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
+
- lr_scheduler_type: linear
|
40 |
+
- num_epochs: 3.0
|
41 |
+
|
42 |
+
### Framework versions
|
43 |
+
|
44 |
+
- Transformers 4.44.2
|
45 |
+
- Pytorch 2.4.0+cu124
|
46 |
+
- Datasets 2.20.0
|
47 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"TraXL"
|
4 |
+
],
|
5 |
+
"dropout": 0.1,
|
6 |
+
"ff_expansion_factor": 8,
|
7 |
+
"hidden_size": 512,
|
8 |
+
"id2label": {
|
9 |
+
"0": "LABEL_0",
|
10 |
+
"1": "LABEL_1",
|
11 |
+
"2": "LABEL_2",
|
12 |
+
"3": "LABEL_3",
|
13 |
+
"4": "LABEL_4"
|
14 |
+
},
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0,
|
17 |
+
"LABEL_1": 1,
|
18 |
+
"LABEL_2": 2,
|
19 |
+
"LABEL_3": 3,
|
20 |
+
"LABEL_4": 4
|
21 |
+
},
|
22 |
+
"max_computation_steps": 10,
|
23 |
+
"max_len": 512,
|
24 |
+
"memory_size": 512,
|
25 |
+
"model_type": "TraXL",
|
26 |
+
"n_embd": 512,
|
27 |
+
"n_head": 8,
|
28 |
+
"n_layer": 8,
|
29 |
+
"rnn_units": 512,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.44.2",
|
32 |
+
"vocab_size": 60000
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9080298ada6e96cab8fe95bcd81df5c81e5bdb7096c62b57fb76e50fab49cf3f
|
3 |
+
size 372079412
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cce9febfb4347c4eb1b0cca71483e49ff7ab3d9c3bb5044e5259cc1e2ea97b1
|
3 |
+
size 5176
|