Dhahlan2000
commited on
Commit
•
3c8784a
1
Parent(s):
e02cfeb
Upload TFMT5ForConditionalGeneration
Browse files- README.md +55 -0
- config.json +31 -0
- generation_config.json +7 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Dhahlan2000/Translation-GPT-v3
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: Translation-GPT-v4
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# Translation-GPT-v4
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [Dhahlan2000/Translation-GPT-v3](https://huggingface.co/Dhahlan2000/Translation-GPT-v3) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.8506
|
19 |
+
- Validation Loss: 2.2484
|
20 |
+
- Epoch: 1
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
40 |
+
- training_precision: float32
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
| Train Loss | Validation Loss | Epoch |
|
45 |
+
|:----------:|:---------------:|:-----:|
|
46 |
+
| 3.0246 | 2.3872 | 0 |
|
47 |
+
| 2.8506 | 2.2484 | 1 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.40.2
|
53 |
+
- TensorFlow 2.15.0
|
54 |
+
- Datasets 2.17.0
|
55 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Dhahlan2000/Translation-GPT-v3",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 1024,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 8,
|
21 |
+
"num_heads": 6,
|
22 |
+
"num_layers": 8,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"tokenizer_class": "T5Tokenizer",
|
28 |
+
"transformers_version": "4.40.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 250112
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.40.2"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be52cca192f29361e8d07670d364593111de51e8e07d7a62666b4a3aa7ed1c93
|
3 |
+
size 2225556280
|