francesco12357
commited on
Commit
•
9d1f853
1
Parent(s):
7e846ac
francesco12357/mixtral_fine_tuned_test
Browse files- README.md +163 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- runs/Feb01_13-40-16_240793099e75/events.out.tfevents.1706794834.240793099e75.961.0 +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 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mixtral-8x7B-v0.1
|
9 |
+
model-index:
|
10 |
+
- name: results_mixtral_sft
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# results_mixtral_sft
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2331
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 10
|
42 |
+
- eval_batch_size: 10
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 20
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 25
|
49 |
+
- num_epochs: 100
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| No log | 1.0 | 1 | 2.4533 |
|
56 |
+
| No log | 2.0 | 2 | 2.4493 |
|
57 |
+
| No log | 3.0 | 3 | 2.4436 |
|
58 |
+
| No log | 4.0 | 4 | 2.4352 |
|
59 |
+
| No log | 5.0 | 5 | 2.4249 |
|
60 |
+
| No log | 6.0 | 6 | 2.4215 |
|
61 |
+
| No log | 7.0 | 7 | 2.4047 |
|
62 |
+
| No log | 8.0 | 8 | 2.3842 |
|
63 |
+
| No log | 9.0 | 9 | 2.3561 |
|
64 |
+
| No log | 10.0 | 10 | 2.3295 |
|
65 |
+
| No log | 11.0 | 11 | 2.3004 |
|
66 |
+
| No log | 12.0 | 12 | 2.2563 |
|
67 |
+
| No log | 13.0 | 13 | 2.2130 |
|
68 |
+
| No log | 14.0 | 14 | 2.1715 |
|
69 |
+
| No log | 15.0 | 15 | 2.1203 |
|
70 |
+
| No log | 16.0 | 16 | 2.0893 |
|
71 |
+
| No log | 17.0 | 17 | 2.0458 |
|
72 |
+
| No log | 18.0 | 18 | 1.9937 |
|
73 |
+
| No log | 19.0 | 19 | 1.9469 |
|
74 |
+
| No log | 20.0 | 20 | 1.9085 |
|
75 |
+
| No log | 21.0 | 21 | 1.9413 |
|
76 |
+
| No log | 22.0 | 22 | 1.8690 |
|
77 |
+
| No log | 23.0 | 23 | 1.8139 |
|
78 |
+
| No log | 24.0 | 24 | 1.7389 |
|
79 |
+
| 1.0996 | 25.0 | 25 | 1.6836 |
|
80 |
+
| 1.0996 | 26.0 | 26 | 1.6236 |
|
81 |
+
| 1.0996 | 27.0 | 27 | 1.5705 |
|
82 |
+
| 1.0996 | 28.0 | 28 | 1.5261 |
|
83 |
+
| 1.0996 | 29.0 | 29 | 1.4790 |
|
84 |
+
| 1.0996 | 30.0 | 30 | 1.4240 |
|
85 |
+
| 1.0996 | 31.0 | 31 | 1.3674 |
|
86 |
+
| 1.0996 | 32.0 | 32 | 1.3182 |
|
87 |
+
| 1.0996 | 33.0 | 33 | 1.2769 |
|
88 |
+
| 1.0996 | 34.0 | 34 | 1.2321 |
|
89 |
+
| 1.0996 | 35.0 | 35 | 1.1885 |
|
90 |
+
| 1.0996 | 36.0 | 36 | 1.1445 |
|
91 |
+
| 1.0996 | 37.0 | 37 | 1.0878 |
|
92 |
+
| 1.0996 | 38.0 | 38 | 1.0237 |
|
93 |
+
| 1.0996 | 39.0 | 39 | 0.9748 |
|
94 |
+
| 1.0996 | 40.0 | 40 | 0.9294 |
|
95 |
+
| 1.0996 | 41.0 | 41 | 0.8806 |
|
96 |
+
| 1.0996 | 42.0 | 42 | 0.8457 |
|
97 |
+
| 1.0996 | 43.0 | 43 | 0.7969 |
|
98 |
+
| 1.0996 | 44.0 | 44 | 0.7599 |
|
99 |
+
| 1.0996 | 45.0 | 45 | 0.7189 |
|
100 |
+
| 1.0996 | 46.0 | 46 | 0.6952 |
|
101 |
+
| 1.0996 | 47.0 | 47 | 0.6570 |
|
102 |
+
| 1.0996 | 48.0 | 48 | 0.6316 |
|
103 |
+
| 1.0996 | 49.0 | 49 | 0.6212 |
|
104 |
+
| 0.548 | 50.0 | 50 | 0.5764 |
|
105 |
+
| 0.548 | 51.0 | 51 | 0.5113 |
|
106 |
+
| 0.548 | 52.0 | 52 | 0.4868 |
|
107 |
+
| 0.548 | 53.0 | 53 | 0.4585 |
|
108 |
+
| 0.548 | 54.0 | 54 | 0.4334 |
|
109 |
+
| 0.548 | 55.0 | 55 | 0.4208 |
|
110 |
+
| 0.548 | 56.0 | 56 | 0.4087 |
|
111 |
+
| 0.548 | 57.0 | 57 | 0.3945 |
|
112 |
+
| 0.548 | 58.0 | 58 | 0.3722 |
|
113 |
+
| 0.548 | 59.0 | 59 | 0.3588 |
|
114 |
+
| 0.548 | 60.0 | 60 | 0.3414 |
|
115 |
+
| 0.548 | 61.0 | 61 | 0.3235 |
|
116 |
+
| 0.548 | 62.0 | 62 | 0.3157 |
|
117 |
+
| 0.548 | 63.0 | 63 | 0.3050 |
|
118 |
+
| 0.548 | 64.0 | 64 | 0.2969 |
|
119 |
+
| 0.548 | 65.0 | 65 | 0.2893 |
|
120 |
+
| 0.548 | 66.0 | 66 | 0.2802 |
|
121 |
+
| 0.548 | 67.0 | 67 | 0.2746 |
|
122 |
+
| 0.548 | 68.0 | 68 | 0.2688 |
|
123 |
+
| 0.548 | 69.0 | 69 | 0.2643 |
|
124 |
+
| 0.548 | 70.0 | 70 | 0.2581 |
|
125 |
+
| 0.548 | 71.0 | 71 | 0.2523 |
|
126 |
+
| 0.548 | 72.0 | 72 | 0.2490 |
|
127 |
+
| 0.548 | 73.0 | 73 | 0.2468 |
|
128 |
+
| 0.548 | 74.0 | 74 | 0.2404 |
|
129 |
+
| 0.1741 | 75.0 | 75 | 0.2394 |
|
130 |
+
| 0.1741 | 76.0 | 76 | 0.2382 |
|
131 |
+
| 0.1741 | 77.0 | 77 | 0.2373 |
|
132 |
+
| 0.1741 | 78.0 | 78 | 0.2366 |
|
133 |
+
| 0.1741 | 79.0 | 79 | 0.2361 |
|
134 |
+
| 0.1741 | 80.0 | 80 | 0.2358 |
|
135 |
+
| 0.1741 | 81.0 | 81 | 0.2355 |
|
136 |
+
| 0.1741 | 82.0 | 82 | 0.2352 |
|
137 |
+
| 0.1741 | 83.0 | 83 | 0.2350 |
|
138 |
+
| 0.1741 | 84.0 | 84 | 0.2348 |
|
139 |
+
| 0.1741 | 85.0 | 85 | 0.2345 |
|
140 |
+
| 0.1741 | 86.0 | 86 | 0.2343 |
|
141 |
+
| 0.1741 | 87.0 | 87 | 0.2342 |
|
142 |
+
| 0.1741 | 88.0 | 88 | 0.2340 |
|
143 |
+
| 0.1741 | 89.0 | 89 | 0.2339 |
|
144 |
+
| 0.1741 | 90.0 | 90 | 0.2337 |
|
145 |
+
| 0.1741 | 91.0 | 91 | 0.2336 |
|
146 |
+
| 0.1741 | 92.0 | 92 | 0.2335 |
|
147 |
+
| 0.1741 | 93.0 | 93 | 0.2334 |
|
148 |
+
| 0.1741 | 94.0 | 94 | 0.2333 |
|
149 |
+
| 0.1741 | 95.0 | 95 | 0.2333 |
|
150 |
+
| 0.1741 | 96.0 | 96 | 0.2332 |
|
151 |
+
| 0.1741 | 97.0 | 97 | 0.2331 |
|
152 |
+
| 0.1741 | 98.0 | 98 | 0.2331 |
|
153 |
+
| 0.1741 | 99.0 | 99 | 0.2331 |
|
154 |
+
| 0.1174 | 100.0 | 100 | 0.2331 |
|
155 |
+
|
156 |
+
|
157 |
+
### Framework versions
|
158 |
+
|
159 |
+
- PEFT 0.8.1
|
160 |
+
- Transformers 4.37.2
|
161 |
+
- Pytorch 2.1.0+cu121
|
162 |
+
- Datasets 2.16.1
|
163 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
|
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": 64,
|
13 |
+
"lora_dropout": 0.1,
|
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 |
+
"k_proj",
|
23 |
+
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c72c8b3f591f6e779884b26d156032892a55f1a8578872534b148a1a1871f78
|
3 |
+
size 54560368
|
runs/Feb01_13-40-16_240793099e75/events.out.tfevents.1706794834.240793099e75.961.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af24159fcb37a3fb55634e98f331999553a6cd29c6c87e8ef6d42bc2792db4d5
|
3 |
+
size 32464
|
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.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": true,
|
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": "<unk>",
|
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 sha256:4fb88393d8e27e4b730fe4d705fe98ed7cd647c17d5f49e1c1d0b5a9408a8f38
|
3 |
+
size 4728
|