Hamana0509
commited on
Commit
•
342eefb
1
Parent(s):
05e576b
Hamana0509/gemma-2-2b-it-Vietnamese-Finetuned
Browse files- README.md +71 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/gemma-2-2b-it
|
3 |
+
library_name: peft
|
4 |
+
license: gemma
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: outputs
|
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 |
+
# outputs
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0013
|
20 |
+
- Model Preparation Time: 0.0212
|
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 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 32
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: cosine
|
47 |
+
- lr_scheduler_warmup_steps: 10
|
48 |
+
- num_epochs: 2
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
|
54 |
+
| 1.1766 | 0.2002 | 390 | 1.2098 | 0.0212 |
|
55 |
+
| 1.2063 | 0.4003 | 780 | 1.1293 | 0.0212 |
|
56 |
+
| 1.063 | 0.6005 | 1170 | 1.0843 | 0.0212 |
|
57 |
+
| 1.0623 | 0.8006 | 1560 | 1.0545 | 0.0212 |
|
58 |
+
| 0.9728 | 1.0008 | 1950 | 1.0336 | 0.0212 |
|
59 |
+
| 0.9455 | 1.2009 | 2340 | 1.0228 | 0.0212 |
|
60 |
+
| 1.0184 | 1.4011 | 2730 | 1.0115 | 0.0212 |
|
61 |
+
| 0.9698 | 1.6012 | 3120 | 1.0042 | 0.0212 |
|
62 |
+
| 0.935 | 1.8014 | 3510 | 1.0013 | 0.0212 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- PEFT 0.13.1
|
68 |
+
- Transformers 4.45.2
|
69 |
+
- Pytorch 2.2.1
|
70 |
+
- Datasets 3.0.1
|
71 |
+
- Tokenizers 0.20.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2-2b-it",
|
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": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"up_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"k_proj",
|
27 |
+
"o_proj",
|
28 |
+
"down_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": true
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00d38884cd16879d5f4f933c1f79ba881e33f26a1f24aa98f1ee53eb4279f0b
|
3 |
+
size 166182480
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4dba467856c169b325b9de32a2b122cd352592b56f952248c16c5207e96734
|
3 |
+
size 5240
|