ihebaker10
commited on
Commit
•
ea9e1de
1
Parent(s):
abe4d0a
End of training
Browse files- README.md +19 -17
- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Apr30_12-57-21_48a6826350b4/events.out.tfevents.1714481843.48a6826350b4.273.0 +3 -0
- special_tokens_map.json +21 -3
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
-
- name: spark-name-
|
10 |
results: []
|
11 |
---
|
12 |
|
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 |
-
# spark-name-
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Bleu:
|
22 |
-
- Gen Len:
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -44,20 +44,22 @@ The following hyperparameters were used during training:
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- num_epochs:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu
|
52 |
-
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
-
- Transformers 4.
|
61 |
-
- Pytorch
|
62 |
-
- Datasets 2.
|
63 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: ihebaker10/spark-name-ar-to-en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
+
- name: spark-name-ar-to-en
|
10 |
results: []
|
11 |
---
|
12 |
|
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 |
+
# spark-name-ar-to-en
|
17 |
|
18 |
+
This model is a fine-tuned version of [ihebaker10/spark-name-ar-to-en](https://huggingface.co/ihebaker10/spark-name-ar-to-en) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.4970
|
21 |
+
- Bleu: 0.0
|
22 |
+
- Gen Len: 4.134
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 5
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:----:|:-------:|
|
53 |
+
| 1.65 | 1.0 | 1000 | 1.4867 | 0.0 | 4.1465 |
|
54 |
+
| 1.3953 | 2.0 | 2000 | 1.4755 | 0.0 | 4.1295 |
|
55 |
+
| 1.2245 | 3.0 | 3000 | 1.4903 | 0.0 | 4.1655 |
|
56 |
+
| 1.1021 | 4.0 | 4000 | 1.4927 | 0.0 | 4.135 |
|
57 |
+
| 1.0237 | 5.0 | 5000 | 1.4970 | 0.0 | 4.134 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
+
- Transformers 4.40.0
|
63 |
+
- Pytorch 2.2.1+cu121
|
64 |
+
- Datasets 2.19.0
|
65 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "swish",
|
@@ -55,7 +55,7 @@
|
|
55 |
"share_encoder_decoder_embeddings": true,
|
56 |
"static_position_embeddings": true,
|
57 |
"torch_dtype": "float32",
|
58 |
-
"transformers_version": "4.
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 62834
|
61 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "ihebaker10/spark-name-ar-to-en",
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "swish",
|
|
|
55 |
"share_encoder_decoder_embeddings": true,
|
56 |
"static_position_embeddings": true,
|
57 |
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.40.0",
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 62834
|
61 |
}
|
generation_config.json
CHANGED
@@ -12,5 +12,5 @@
|
|
12 |
"num_beams": 4,
|
13 |
"pad_token_id": 62833,
|
14 |
"renormalize_logits": true,
|
15 |
-
"transformers_version": "4.
|
16 |
}
|
|
|
12 |
"num_beams": 4,
|
13 |
"pad_token_id": 62833,
|
14 |
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.40.0"
|
16 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 305518408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39520a1a8f8f949f3cc9c5bd1b1c4617b00d7a89c10068e23d87fd5cc370a00f
|
3 |
size 305518408
|
runs/Apr30_12-57-21_48a6826350b4/events.out.tfevents.1714481843.48a6826350b4.273.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c1abe83a826b531cf336b0ef1d3dc8aea7e551c82b2e5476ac22ac981143b6a
|
3 |
+
size 9920
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,23 @@
|
|
1 |
{
|
2 |
-
"eos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9224d4dab0478e2ca1d514b435d161294cdf653c08d944eb81c3776295877f5b
|
3 |
+
size 5176
|