Cem13 commited on
Commit
a045772
1 Parent(s): 99d6b3e
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-Instruct-v0.1
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: mistral_instruct_generation
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # mistral_instruct_generation
20
+
21
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.8488
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: constant
48
+ - lr_scheduler_warmup_steps: 0.03
49
+ - training_steps: 500
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.1973 | 0.0305 | 20 | 1.1052 |
56
+ | 1.0347 | 0.0610 | 40 | 0.9958 |
57
+ | 0.9213 | 0.0915 | 60 | 0.9600 |
58
+ | 0.8886 | 0.1220 | 80 | 0.9406 |
59
+ | 0.9314 | 0.1524 | 100 | 0.9281 |
60
+ | 0.9668 | 0.1829 | 120 | 0.9197 |
61
+ | 0.887 | 0.2134 | 140 | 0.9128 |
62
+ | 0.8727 | 0.2439 | 160 | 0.9066 |
63
+ | 0.8571 | 0.2744 | 180 | 0.9005 |
64
+ | 0.8833 | 0.3049 | 200 | 0.8963 |
65
+ | 0.8466 | 0.3354 | 220 | 0.8912 |
66
+ | 0.9015 | 0.3659 | 240 | 0.8865 |
67
+ | 0.8602 | 0.3963 | 260 | 0.8822 |
68
+ | 0.8989 | 0.4268 | 280 | 0.8788 |
69
+ | 0.8452 | 0.4573 | 300 | 0.8758 |
70
+ | 0.8764 | 0.4878 | 320 | 0.8730 |
71
+ | 0.8702 | 0.5183 | 340 | 0.8708 |
72
+ | 0.8758 | 0.5488 | 360 | 0.8676 |
73
+ | 0.8071 | 0.5793 | 380 | 0.8638 |
74
+ | 0.8473 | 0.6098 | 400 | 0.8618 |
75
+ | 0.8822 | 0.6402 | 420 | 0.8586 |
76
+ | 0.8742 | 0.6707 | 440 | 0.8560 |
77
+ | 0.8526 | 0.7012 | 460 | 0.8533 |
78
+ | 0.8116 | 0.7317 | 480 | 0.8511 |
79
+ | 0.8593 | 0.7622 | 500 | 0.8488 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - PEFT 0.10.0
85
+ - Transformers 4.40.1
86
+ - Pytorch 2.3.0+cu121
87
+ - Datasets 2.19.0
88
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
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": 16,
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": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4aa942f48fe19334df4762e441341f93a95535c64d66af94cadbc8c0c053cc
3
+ size 109069176
runs/Apr28_18-37-54_1cdde9d44bc6/events.out.tfevents.1714329481.1cdde9d44bc6.352.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700772558c9e74c97080a97e1c1d4cae11cc86bcb46dff9b21c4e476dadf3760
3
+ size 22797
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429ffc72cf8a2e9794f479a3ee523ab775d1474d15df35a4be71eddd76c023c2
3
+ size 5048