Casper0508
commited on
Commit
•
ae7e37b
1
Parent(s):
134693e
End of training
Browse files- README.md +100 -0
- adapter_config.json +23 -0
- adapter_model.safetensors +3 -0
- emissions.csv +2 -0
- runs/Jun23_11-29-16_msc-modeltrain-pod2/events.out.tfevents.1719142159.msc-modeltrain-pod2.12263.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
base_model: meta-llama/Llama-2-7b-chat-hf
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: MSc_llama2_finetuned_model_secondData7
|
8 |
+
results: []
|
9 |
+
library_name: peft
|
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 |
+
# MSc_llama2_finetuned_model_secondData7
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.6939
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
|
36 |
+
The following `bitsandbytes` quantization config was used during training:
|
37 |
+
- quant_method: bitsandbytes
|
38 |
+
- _load_in_8bit: False
|
39 |
+
- _load_in_4bit: True
|
40 |
+
- llm_int8_threshold: 6.0
|
41 |
+
- llm_int8_skip_modules: None
|
42 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
43 |
+
- llm_int8_has_fp16_weight: False
|
44 |
+
- bnb_4bit_quant_type: nf4
|
45 |
+
- bnb_4bit_use_double_quant: True
|
46 |
+
- bnb_4bit_compute_dtype: bfloat16
|
47 |
+
- load_in_4bit: True
|
48 |
+
- load_in_8bit: False
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 3e-05
|
53 |
+
- train_batch_size: 32
|
54 |
+
- eval_batch_size: 8
|
55 |
+
- seed: 42
|
56 |
+
- gradient_accumulation_steps: 2
|
57 |
+
- total_train_batch_size: 64
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: cosine
|
60 |
+
- lr_scheduler_warmup_ratio: 0.03
|
61 |
+
- training_steps: 250
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
+
| 3.9823 | 1.33 | 10 | 3.6153 |
|
68 |
+
| 3.3928 | 2.67 | 20 | 2.9413 |
|
69 |
+
| 2.6305 | 4.0 | 30 | 2.1743 |
|
70 |
+
| 1.9546 | 5.33 | 40 | 1.7079 |
|
71 |
+
| 1.5996 | 6.67 | 50 | 1.4500 |
|
72 |
+
| 1.2984 | 8.0 | 60 | 1.1277 |
|
73 |
+
| 0.9632 | 9.33 | 70 | 0.8761 |
|
74 |
+
| 0.8296 | 10.67 | 80 | 0.8206 |
|
75 |
+
| 0.7589 | 12.0 | 90 | 0.7735 |
|
76 |
+
| 0.7063 | 13.33 | 100 | 0.7446 |
|
77 |
+
| 0.671 | 14.67 | 110 | 0.7278 |
|
78 |
+
| 0.6405 | 16.0 | 120 | 0.7091 |
|
79 |
+
| 0.6096 | 17.33 | 130 | 0.7021 |
|
80 |
+
| 0.5845 | 18.67 | 140 | 0.6986 |
|
81 |
+
| 0.5697 | 20.0 | 150 | 0.6938 |
|
82 |
+
| 0.5539 | 21.33 | 160 | 0.6936 |
|
83 |
+
| 0.5414 | 22.67 | 170 | 0.6913 |
|
84 |
+
| 0.5313 | 24.0 | 180 | 0.6920 |
|
85 |
+
| 0.522 | 25.33 | 190 | 0.6919 |
|
86 |
+
| 0.5168 | 26.67 | 200 | 0.6932 |
|
87 |
+
| 0.5191 | 28.0 | 210 | 0.6942 |
|
88 |
+
| 0.5079 | 29.33 | 220 | 0.6938 |
|
89 |
+
| 0.5132 | 30.67 | 230 | 0.6939 |
|
90 |
+
| 0.5085 | 32.0 | 240 | 0.6939 |
|
91 |
+
| 0.5079 | 33.33 | 250 | 0.6939 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- PEFT 0.4.0
|
97 |
+
- Transformers 4.38.2
|
98 |
+
- Pytorch 2.3.1+cu121
|
99 |
+
- Datasets 2.13.1
|
100 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 64,
|
11 |
+
"lora_dropout": 0.2,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 32,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"k_proj",
|
19 |
+
"v_proj",
|
20 |
+
"out_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef6abb4a233b794fb436b030ba63d004c16182a205d293ced8c7de9db92d57ed
|
3 |
+
size 100689152
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
+
2024-06-23T12:11:11,a8a6ee75-5f55-409c-b52f-78db4791d31a,codecarbon,2512.0242128372192,0.15779039742691128,0.23476903939865856,United Kingdom,GBR,scotland,N,,
|
runs/Jun23_11-29-16_msc-modeltrain-pod2/events.out.tfevents.1719142159.msc-modeltrain-pod2.12263.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:593ba8cdcf0855862c88f458ad512c04d81fe94beaa46d0803dc46cbb31d4963
|
3 |
+
size 17463
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
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 sha256:2cf547a33543e8280dbac03e3c370dedc1df845fc6fb9094abf530da6d17bbbc
|
3 |
+
size 4984
|