hussamsal/Mistral-7b-Resumes
Browse files- README.md +91 -0
- adapter_config.json +23 -0
- adapter_model.safetensors +3 -0
- runs/May01_16-34-28_5c8c2c17c6a2/events.out.tfevents.1714581289.5c8c2c17c6a2.841.11 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: final_model-3
|
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 |
+
# final_model-3
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.0656
|
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: False
|
46 |
+
- bnb_4bit_compute_dtype: float16
|
47 |
+
### Training hyperparameters
|
48 |
+
|
49 |
+
The following hyperparameters were used during training:
|
50 |
+
- learning_rate: 0.0002
|
51 |
+
- train_batch_size: 4
|
52 |
+
- eval_batch_size: 4
|
53 |
+
- seed: 42
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: cosine
|
56 |
+
- lr_scheduler_warmup_ratio: 0.03
|
57 |
+
- training_steps: 20
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
62 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
63 |
+
| 2.4774 | 0.0 | 1 | 2.3519 |
|
64 |
+
| 2.3907 | 0.01 | 2 | 2.2619 |
|
65 |
+
| 2.2831 | 0.01 | 3 | 2.1934 |
|
66 |
+
| 2.3523 | 0.02 | 4 | 2.1535 |
|
67 |
+
| 2.2008 | 0.02 | 5 | 2.1415 |
|
68 |
+
| 2.398 | 0.02 | 6 | 2.1336 |
|
69 |
+
| 2.0323 | 0.03 | 7 | 2.1223 |
|
70 |
+
| 1.9787 | 0.03 | 8 | 2.1102 |
|
71 |
+
| 2.2163 | 0.04 | 9 | 2.1011 |
|
72 |
+
| 2.4075 | 0.04 | 10 | 2.0942 |
|
73 |
+
| 2.0822 | 0.04 | 11 | 2.0878 |
|
74 |
+
| 2.3128 | 0.05 | 12 | 2.0823 |
|
75 |
+
| 1.9674 | 0.05 | 13 | 2.0775 |
|
76 |
+
| 2.0991 | 0.06 | 14 | 2.0739 |
|
77 |
+
| 2.1918 | 0.06 | 15 | 2.0707 |
|
78 |
+
| 2.0037 | 0.06 | 16 | 2.0684 |
|
79 |
+
| 2.0398 | 0.07 | 17 | 2.0669 |
|
80 |
+
| 2.1113 | 0.07 | 18 | 2.0661 |
|
81 |
+
| 1.9206 | 0.08 | 19 | 2.0657 |
|
82 |
+
| 1.6649 | 0.08 | 20 | 2.0656 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- PEFT 0.4.0
|
88 |
+
- Transformers 4.37.2
|
89 |
+
- Pytorch 2.2.1+cu121
|
90 |
+
- Datasets 2.19.0
|
91 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
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": 16,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"o_proj",
|
19 |
+
"k_proj",
|
20 |
+
"v_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 sha256:7c9b88034af257749d65c0f1a0cfbd485fd01462ae3bb7c40b32029d7d898a99
|
3 |
+
size 218138576
|
runs/May01_16-34-28_5c8c2c17c6a2/events.out.tfevents.1714581289.5c8c2c17c6a2.841.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:551e8dfc3af53a5337c7a3099bccab9a2a92fa95a3e8f5cdcb0210738b605632
|
3 |
+
size 13601
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e598acbf64830a97ca02f09937562dc7d503616af143f51281f55f1c93c1fb6e
|
3 |
+
size 4728
|