KEITA21/rebel-large
Browse files- README.md +53 -0
- adapter_config.json +45 -0
- adapter_model.safetensors +3 -0
- epoch_losses.csv +4 -0
- training_args.bin +3 -0
- training_losses.csv +1 -0
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: Babelscape/rebel-large
|
7 |
+
model-index:
|
8 |
+
- name: rebel
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# rebel
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [Babelscape/rebel-large](https://huggingface.co/Babelscape/rebel-large) on the None dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 5e-08
|
37 |
+
- train_batch_size: 10
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 10
|
41 |
+
- total_train_batch_size: 100
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- PEFT 0.11.1
|
50 |
+
- Transformers 4.40.1
|
51 |
+
- Pytorch 2.3.0+cu121
|
52 |
+
- Datasets 2.19.0
|
53 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Babelscape/rebel-large",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 180,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"model.encoder.layers.11.self_attn.q_proj",
|
24 |
+
"model.decoder.layers.11.encoder_attn.q_proj",
|
25 |
+
"model.encoder.layers.11.self_attn.k_proj",
|
26 |
+
"model.encoder.layers.10.self_attn.q_proj",
|
27 |
+
"model.decoder.layers.10.encoder_attn.q_proj",
|
28 |
+
"model.decoder.layers.11.self_attn.q_proj",
|
29 |
+
"model.decoder.layers.10.self_attn.k_proj",
|
30 |
+
"model.encoder.layers.10.self_attn.v_proj",
|
31 |
+
"model.decoder.layers.10.encoder_attn.v_proj",
|
32 |
+
"model.decoder.layers.10.self_attn.q_proj",
|
33 |
+
"model.encoder.layers.11.self_attn.v_proj",
|
34 |
+
"model.decoder.layers.10.self_attn.v_proj",
|
35 |
+
"model.encoder.layers.10.self_attn.k_proj",
|
36 |
+
"model.decoder.layers.11.self_attn.v_proj",
|
37 |
+
"model.decoder.layers.11.encoder_attn.k_proj",
|
38 |
+
"model.decoder.layers.10.encoder_attn.k_proj",
|
39 |
+
"model.decoder.layers.11.encoder_attn.v_proj",
|
40 |
+
"model.decoder.layers.11.self_attn.k_proj"
|
41 |
+
],
|
42 |
+
"task_type": "text2text-generation",
|
43 |
+
"use_dora": false,
|
44 |
+
"use_rslora": false
|
45 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:470e7cca413a1f98fd979d414d264c40194c15e88efee06cbde9137a1527ce18
|
3 |
+
size 26547312
|
epoch_losses.csv
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
,epoch_loss
|
2 |
+
0,0.0
|
3 |
+
1,0.0
|
4 |
+
2,0.0
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41e236bee96e8a583d06831047d6f187170448367fac38a0a68e6197d9723823
|
3 |
+
size 4920
|
training_losses.csv
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
,loss
|