yaeeun commited on
Commit
9b173cc
1 Parent(s): 09b31a0

yaeeun/lora-midm-7b-nsmc-review

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: KT-AI/midm-bitext-S-7B-inst-v1
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: lora-midm-7b-nsmc-review-understanding
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
+ # lora-midm-7b-nsmc-review-understanding
15
+
16
+ This model is a fine-tuned version of [KT-AI/midm-bitext-S-7B-inst-v1](https://huggingface.co/KT-AI/midm-bitext-S-7B-inst-v1) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0001
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 1
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 2
40
+ - total_train_batch_size: 2
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_ratio: 0.03
44
+ - training_steps: 200
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.35.2
54
+ - Pytorch 2.1.0+cu118
55
+ - Datasets 2.15.0
56
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "KT-AI/midm-bitext-S-7B-inst-v1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "c_proj",
23
+ "c_attn",
24
+ "c_fc"
25
+ ],
26
+ "task_type": "CAUSAL_LM"
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162575e755de12dc3f3505cb6ef1a9ebc753a1907c2cd82b1351a85afdb2d2ee
3
+ size 67010784
midm_bitext_tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98789fa1bf89a1f9692889fb4a0029d3d096a9109cebf4f6bce1a255f2701378
3
+ size 1457356
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": "</s>",
10
+ "pad_token": "<pad>",
11
+ "unk_token": "<unk>"
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "auto_map": {
38
+ "AutoTokenizer": [
39
+ "KT-AI/midm-bitext-S-7B-inst-v1--midm_bitext_tokenization.Midm_bitext_Tokenizer",
40
+ null
41
+ ]
42
+ },
43
+ "bos_token": "<s>",
44
+ "clean_up_tokenization_spaces": true,
45
+ "eos_token": "</s>",
46
+ "extra_ids": 0,
47
+ "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "<pad>",
49
+ "sp_model_kwargs": {},
50
+ "tokenizer_class": "Midm_bitext_Tokenizer",
51
+ "unk_token": "<unk>"
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e3449474e9bdcaee5fb10665ee5b8d6d5f72e99686b1bb4ab6454b4ccc104b0
3
+ size 4664