End of training
Browse files- README.md +90 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: Mistral-7B-Instruct-v0.2-absa-MT-laptops
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# Mistral-7B-Instruct-v0.2-absa-MT-laptops
|
15 |
+
|
16 |
+
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.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0064
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 3e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 4
|
42 |
+
- total_train_batch_size: 32
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 2
|
46 |
+
- training_steps: 1200
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 0.866 | 0.13 | 40 | 0.1399 |
|
54 |
+
| 0.066 | 0.25 | 80 | 0.0188 |
|
55 |
+
| 0.0151 | 0.38 | 120 | 0.0152 |
|
56 |
+
| 0.0137 | 0.5 | 160 | 0.0141 |
|
57 |
+
| 0.0133 | 0.63 | 200 | 0.0130 |
|
58 |
+
| 0.0124 | 0.75 | 240 | 0.0115 |
|
59 |
+
| 0.009 | 0.88 | 280 | 0.0109 |
|
60 |
+
| 0.0105 | 1.0 | 320 | 0.0106 |
|
61 |
+
| 0.0069 | 1.13 | 360 | 0.0098 |
|
62 |
+
| 0.0069 | 1.25 | 400 | 0.0095 |
|
63 |
+
| 0.0074 | 1.38 | 440 | 0.0086 |
|
64 |
+
| 0.0069 | 1.5 | 480 | 0.0085 |
|
65 |
+
| 0.0057 | 1.63 | 520 | 0.0090 |
|
66 |
+
| 0.0065 | 1.75 | 560 | 0.0085 |
|
67 |
+
| 0.0069 | 1.88 | 600 | 0.0077 |
|
68 |
+
| 0.0053 | 2.0 | 640 | 0.0076 |
|
69 |
+
| 0.0037 | 2.13 | 680 | 0.0074 |
|
70 |
+
| 0.0036 | 2.25 | 720 | 0.0072 |
|
71 |
+
| 0.0034 | 2.38 | 760 | 0.0071 |
|
72 |
+
| 0.0038 | 2.5 | 800 | 0.0067 |
|
73 |
+
| 0.0032 | 2.63 | 840 | 0.0063 |
|
74 |
+
| 0.0029 | 2.75 | 880 | 0.0066 |
|
75 |
+
| 0.003 | 2.88 | 920 | 0.0060 |
|
76 |
+
| 0.0022 | 3.0 | 960 | 0.0060 |
|
77 |
+
| 0.0014 | 3.13 | 1000 | 0.0062 |
|
78 |
+
| 0.0012 | 3.26 | 1040 | 0.0064 |
|
79 |
+
| 0.0011 | 3.38 | 1080 | 0.0066 |
|
80 |
+
| 0.0011 | 3.51 | 1120 | 0.0065 |
|
81 |
+
| 0.0012 | 3.63 | 1160 | 0.0063 |
|
82 |
+
| 0.0014 | 3.76 | 1200 | 0.0064 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- Transformers 4.38.2
|
88 |
+
- Pytorch 2.2.1+cu121
|
89 |
+
- Datasets 2.18.0
|
90 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
3 |
+
"bias": "none",
|
4 |
+
"enable_lora": null,
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"lora_alpha": 64,
|
8 |
+
"lora_dropout": 0.05,
|
9 |
+
"merge_weights": false,
|
10 |
+
"modules_to_save": null,
|
11 |
+
"peft_type": "LORA",
|
12 |
+
"r": 64,
|
13 |
+
"target_modules": [
|
14 |
+
"q_proj",
|
15 |
+
"v_proj",
|
16 |
+
"k_proj",
|
17 |
+
"o_proj"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a914335b2e7214c7a1ab5ba35e8050329d2e5bc09aa36d4319ab07b40e1296d4
|
3 |
+
size 218196746
|
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": "<unk>",
|
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_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": "<unk>",
|
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 sha256:24b0dc37328cc8b51f047d521e3b6593f542de613d12e4c7dbd35ba8290a2110
|
3 |
+
size 4984
|