hilaltekgoz
commited on
Commit
•
f31dc3d
1
Parent(s):
c0d0fec
End of training
Browse files- README.md +58 -0
- config.json +35 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Mar17_21-45-29_dd99467f690a/events.out.tfevents.1710711930.dd99467f690a.1311.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: agemagician/mlong-t5-tglobal-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: paraphraset5gl
|
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 |
+
# paraphraset5gl
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [agemagician/mlong-t5-tglobal-base](https://huggingface.co/agemagician/mlong-t5-tglobal-base) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4972
|
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-05
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 2
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 12.3413 | 1.0 | 915 | 0.6540 |
|
50 |
+
| 0.7972 | 2.0 | 1830 | 0.4972 |
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.39.0.dev0
|
56 |
+
- Pytorch 2.2.1+cu121
|
57 |
+
- Datasets 2.18.0
|
58 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "agemagician/mlong-t5-tglobal-base",
|
3 |
+
"architectures": [
|
4 |
+
"LongT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"encoder_attention_type": "transient-global",
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"global_block_size": 16,
|
16 |
+
"initializer_factor": 1.0,
|
17 |
+
"is_encoder_decoder": true,
|
18 |
+
"is_gated_act": true,
|
19 |
+
"layer_norm_epsilon": 1e-06,
|
20 |
+
"local_radius": 127,
|
21 |
+
"model_type": "longt5",
|
22 |
+
"n_positions": 4096,
|
23 |
+
"num_decoder_layers": 12,
|
24 |
+
"num_heads": 12,
|
25 |
+
"num_layers": 12,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"relative_attention_max_distance": 128,
|
29 |
+
"relative_attention_num_buckets": 32,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.39.0.dev0",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 256384
|
35 |
+
}
|
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": "4.39.0.dev0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f423fbdda311e025db53a2e70348d441447698c59cbde33b1bcc66ddf6d2d4d2
|
3 |
+
size 2368215072
|
runs/Mar17_21-45-29_dd99467f690a/events.out.tfevents.1710711930.dd99467f690a.1311.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94225653ebba0648bbfd8c6d1447df177b83e5cb3e8ba9d4c0aab41e60d977c8
|
3 |
+
size 6416
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bff03e46e465c76946dee4bd58d7eeb197e377da6db447d8a67c07be382b825
|
3 |
+
size 4920
|