lillybak commited on
Commit
a81cd1a
1 Parent(s): a79da71

lillybak/llama2-instruct-tune-500.v1

Browse files
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - trl
5
+ - sft
6
+ - generated_from_trainer
7
+ datasets:
8
+ - generator
9
+ base_model: NousResearch/Llama-2-7b-hf
10
+ model-index:
11
+ - name: output_llama2_instruct
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # output_llama2_instruct
19
+
20
+ This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the generator dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.6746
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0002
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: constant
47
+ - lr_scheduler_warmup_steps: 20
48
+ - training_steps: 500
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.9193 | 0.0 | 20 | 1.8124 |
55
+ | 1.8847 | 0.01 | 40 | 1.7835 |
56
+ | 1.813 | 0.01 | 60 | 1.7710 |
57
+ | 1.9026 | 0.01 | 80 | 1.7605 |
58
+ | 1.8352 | 0.01 | 100 | 1.7449 |
59
+ | 1.7327 | 0.02 | 120 | 1.7100 |
60
+ | 1.8625 | 0.02 | 140 | 1.7055 |
61
+ | 1.9379 | 0.02 | 160 | 1.7008 |
62
+ | 1.8597 | 0.02 | 180 | 1.6971 |
63
+ | 1.8703 | 0.03 | 200 | 1.6943 |
64
+ | 1.7749 | 0.03 | 220 | 1.6902 |
65
+ | 1.7645 | 0.03 | 240 | 1.6898 |
66
+ | 1.7894 | 0.04 | 260 | 1.6886 |
67
+ | 1.8492 | 0.04 | 280 | 1.6870 |
68
+ | 1.7331 | 0.04 | 300 | 1.6841 |
69
+ | 1.7278 | 0.04 | 320 | 1.6830 |
70
+ | 1.6963 | 0.05 | 340 | 1.6826 |
71
+ | 1.8226 | 0.05 | 360 | 1.6813 |
72
+ | 1.8246 | 0.05 | 380 | 1.6797 |
73
+ | 1.8577 | 0.05 | 400 | 1.6778 |
74
+ | 1.6691 | 0.06 | 420 | 1.6779 |
75
+ | 1.7001 | 0.06 | 440 | 1.6774 |
76
+ | 1.9008 | 0.06 | 460 | 1.6770 |
77
+ | 1.7856 | 0.07 | 480 | 1.6733 |
78
+ | 1.7674 | 0.07 | 500 | 1.6746 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - PEFT 0.8.2
84
+ - Transformers 4.37.2
85
+ - Pytorch 2.1.0+cu121
86
+ - Datasets 2.16.1
87
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
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": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
3
+ size 48
runs/Feb08_06-57-55_60adb62959b1/events.out.tfevents.1707375857.60adb62959b1.747.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc55a8b7166ad112c4307c5f091035ae1f3f26daaa508423e510febdb462c26f
3
+ size 19742
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e53fbd74ba50bbf0a5ec61f2e46d6c8e3154ad4a84e91ed000b24e5c30e530b
3
+ size 4728