fernandals commited on
Commit
e365ac6
1 Parent(s): 4cbd0c4

Uploading model

Browse files
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - trl
5
+ - sft
6
+ - generated_from_trainer
7
+ base_model: NousResearch/Llama-2-7b-hf
8
+ model-index:
9
+ - name: results
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # results
17
+
18
+ This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.9343
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: 0.0002
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 16
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 10
48
+ - num_epochs: 4
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.7949 | 0.1 | 25 | 1.7390 |
55
+ | 1.7268 | 0.21 | 50 | 1.6898 |
56
+ | 1.7214 | 0.31 | 75 | 1.6547 |
57
+ | 1.6573 | 0.41 | 100 | 1.6260 |
58
+ | 1.6663 | 0.52 | 125 | 1.5999 |
59
+ | 1.6499 | 0.62 | 150 | 1.5735 |
60
+ | 1.61 | 0.72 | 175 | 1.5483 |
61
+ | 1.6491 | 0.82 | 200 | 1.5288 |
62
+ | 1.6441 | 0.93 | 225 | 1.5034 |
63
+ | 1.5055 | 1.03 | 250 | 1.4753 |
64
+ | 1.4955 | 1.13 | 275 | 1.4409 |
65
+ | 1.4345 | 1.24 | 300 | 1.4159 |
66
+ | 1.449 | 1.34 | 325 | 1.3918 |
67
+ | 1.4762 | 1.44 | 350 | 1.3701 |
68
+ | 1.4562 | 1.55 | 375 | 1.3449 |
69
+ | 1.4092 | 1.65 | 400 | 1.3205 |
70
+ | 1.4173 | 1.75 | 425 | 1.3000 |
71
+ | 1.4225 | 1.86 | 450 | 1.2798 |
72
+ | 1.4358 | 1.96 | 475 | 1.2600 |
73
+ | 1.2387 | 2.06 | 500 | 1.2198 |
74
+ | 1.232 | 2.16 | 525 | 1.1936 |
75
+ | 1.2212 | 2.27 | 550 | 1.1720 |
76
+ | 1.2066 | 2.37 | 575 | 1.1491 |
77
+ | 1.199 | 2.47 | 600 | 1.1301 |
78
+ | 1.2365 | 2.58 | 625 | 1.1124 |
79
+ | 1.2124 | 2.68 | 650 | 1.0934 |
80
+ | 1.2113 | 2.78 | 675 | 1.0766 |
81
+ | 1.1947 | 2.89 | 700 | 1.0620 |
82
+ | 1.2041 | 2.99 | 725 | 1.0441 |
83
+ | 1.0437 | 3.09 | 750 | 1.0133 |
84
+ | 1.0239 | 3.2 | 775 | 0.9972 |
85
+ | 1.0417 | 3.3 | 800 | 0.9839 |
86
+ | 0.9909 | 3.4 | 825 | 0.9712 |
87
+ | 1.0275 | 3.51 | 850 | 0.9600 |
88
+ | 1.0466 | 3.61 | 875 | 0.9516 |
89
+ | 1.0036 | 3.71 | 900 | 0.9423 |
90
+ | 1.0039 | 3.81 | 925 | 0.9363 |
91
+ | 0.9786 | 3.92 | 950 | 0.9343 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - PEFT 0.8.2
97
+ - Transformers 4.37.2
98
+ - Pytorch 2.2.0+cu121
99
+ - Datasets 2.17.0
100
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 32,
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": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "v_proj",
24
+ "down_proj",
25
+ "q_proj",
26
+ "gate_proj",
27
+ "up_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdded58809f4dc2a5ede638f6be88e7e68d786478bd77cf0210569731f76b044
3
+ size 134
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": "<unk>",
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 sha256:1a8f238a200be6c23fbba0f9a999ab4fe3c09ca303b29805e68cf6659bfb7d89
3
+ size 131
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": "<unk>",
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 sha256:7d2357f378cbb833b3fbeea9aa1445f096b5fb34c4c483e055e5b6a7bcf18015
3
+ size 129