Commit
•
0f239a8
1
Parent(s):
5eee000
End of training
Browse files- README.md +188 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
7 |
+
model-index:
|
8 |
+
- name: Mixtral-8x7B-Instruct-v0.1
|
9 |
+
results: []
|
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 |
+
# Mixtral-8x7B-Instruct-v0.1
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.3898
|
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 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 1
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 1.8837 | 0.01 | 5 | 1.7824 |
|
52 |
+
| 1.8578 | 0.02 | 10 | 1.7336 |
|
53 |
+
| 1.6828 | 0.02 | 15 | 1.6999 |
|
54 |
+
| 1.8063 | 0.03 | 20 | 1.6716 |
|
55 |
+
| 1.6728 | 0.04 | 25 | 1.6400 |
|
56 |
+
| 1.5326 | 0.05 | 30 | 1.6079 |
|
57 |
+
| 1.5742 | 0.05 | 35 | 1.5795 |
|
58 |
+
| 1.6315 | 0.06 | 40 | 1.5597 |
|
59 |
+
| 1.6111 | 0.07 | 45 | 1.5449 |
|
60 |
+
| 1.5815 | 0.08 | 50 | 1.5359 |
|
61 |
+
| 1.4937 | 0.09 | 55 | 1.5234 |
|
62 |
+
| 1.4524 | 0.09 | 60 | 1.5177 |
|
63 |
+
| 1.4922 | 0.1 | 65 | 1.5150 |
|
64 |
+
| 1.5636 | 0.11 | 70 | 1.5058 |
|
65 |
+
| 1.5303 | 0.12 | 75 | 1.5020 |
|
66 |
+
| 1.4182 | 0.12 | 80 | 1.5003 |
|
67 |
+
| 1.4375 | 0.13 | 85 | 1.4919 |
|
68 |
+
| 1.4287 | 0.14 | 90 | 1.4873 |
|
69 |
+
| 1.5023 | 0.15 | 95 | 1.4859 |
|
70 |
+
| 1.5331 | 0.16 | 100 | 1.4800 |
|
71 |
+
| 1.4797 | 0.16 | 105 | 1.4784 |
|
72 |
+
| 1.476 | 0.17 | 110 | 1.4741 |
|
73 |
+
| 1.5398 | 0.18 | 115 | 1.4702 |
|
74 |
+
| 1.4086 | 0.19 | 120 | 1.4670 |
|
75 |
+
| 1.4222 | 0.19 | 125 | 1.4648 |
|
76 |
+
| 1.4033 | 0.2 | 130 | 1.4623 |
|
77 |
+
| 1.5386 | 0.21 | 135 | 1.4608 |
|
78 |
+
| 1.4959 | 0.22 | 140 | 1.4583 |
|
79 |
+
| 1.4908 | 0.22 | 145 | 1.4542 |
|
80 |
+
| 1.4669 | 0.23 | 150 | 1.4510 |
|
81 |
+
| 1.4733 | 0.24 | 155 | 1.4477 |
|
82 |
+
| 1.5692 | 0.25 | 160 | 1.4458 |
|
83 |
+
| 1.484 | 0.26 | 165 | 1.4468 |
|
84 |
+
| 1.4186 | 0.26 | 170 | 1.4432 |
|
85 |
+
| 1.3907 | 0.27 | 175 | 1.4391 |
|
86 |
+
| 1.4489 | 0.28 | 180 | 1.4392 |
|
87 |
+
| 1.471 | 0.29 | 185 | 1.4364 |
|
88 |
+
| 1.31 | 0.29 | 190 | 1.4344 |
|
89 |
+
| 1.3949 | 0.3 | 195 | 1.4324 |
|
90 |
+
| 1.4094 | 0.31 | 200 | 1.4306 |
|
91 |
+
| 1.4235 | 0.32 | 205 | 1.4275 |
|
92 |
+
| 1.5056 | 0.33 | 210 | 1.4271 |
|
93 |
+
| 1.4281 | 0.33 | 215 | 1.4251 |
|
94 |
+
| 1.4329 | 0.34 | 220 | 1.4236 |
|
95 |
+
| 1.3791 | 0.35 | 225 | 1.4221 |
|
96 |
+
| 1.4189 | 0.36 | 230 | 1.4207 |
|
97 |
+
| 1.4192 | 0.36 | 235 | 1.4198 |
|
98 |
+
| 1.3807 | 0.37 | 240 | 1.4187 |
|
99 |
+
| 1.4362 | 0.38 | 245 | 1.4177 |
|
100 |
+
| 1.419 | 0.39 | 250 | 1.4174 |
|
101 |
+
| 1.5039 | 0.4 | 255 | 1.4176 |
|
102 |
+
| 1.4323 | 0.4 | 260 | 1.4160 |
|
103 |
+
| 1.5249 | 0.41 | 265 | 1.4154 |
|
104 |
+
| 1.4462 | 0.42 | 270 | 1.4144 |
|
105 |
+
| 1.2841 | 0.43 | 275 | 1.4137 |
|
106 |
+
| 1.3764 | 0.43 | 280 | 1.4137 |
|
107 |
+
| 1.3063 | 0.44 | 285 | 1.4123 |
|
108 |
+
| 1.4296 | 0.45 | 290 | 1.4122 |
|
109 |
+
| 1.4333 | 0.46 | 295 | 1.4110 |
|
110 |
+
| 1.3113 | 0.47 | 300 | 1.4103 |
|
111 |
+
| 1.3138 | 0.47 | 305 | 1.4103 |
|
112 |
+
| 1.3951 | 0.48 | 310 | 1.4104 |
|
113 |
+
| 1.3592 | 0.49 | 315 | 1.4099 |
|
114 |
+
| 1.458 | 0.5 | 320 | 1.4094 |
|
115 |
+
| 1.4037 | 0.5 | 325 | 1.4094 |
|
116 |
+
| 1.4431 | 0.51 | 330 | 1.4086 |
|
117 |
+
| 1.3595 | 0.52 | 335 | 1.4076 |
|
118 |
+
| 1.3198 | 0.53 | 340 | 1.4061 |
|
119 |
+
| 1.3967 | 0.53 | 345 | 1.4054 |
|
120 |
+
| 1.254 | 0.54 | 350 | 1.4049 |
|
121 |
+
| 1.3324 | 0.55 | 355 | 1.4047 |
|
122 |
+
| 1.2428 | 0.56 | 360 | 1.4037 |
|
123 |
+
| 1.3976 | 0.57 | 365 | 1.4033 |
|
124 |
+
| 1.4226 | 0.57 | 370 | 1.4036 |
|
125 |
+
| 1.3678 | 0.58 | 375 | 1.4038 |
|
126 |
+
| 1.4634 | 0.59 | 380 | 1.4028 |
|
127 |
+
| 1.4325 | 0.6 | 385 | 1.4018 |
|
128 |
+
| 1.3175 | 0.6 | 390 | 1.4013 |
|
129 |
+
| 1.3263 | 0.61 | 395 | 1.4007 |
|
130 |
+
| 1.3653 | 0.62 | 400 | 1.4019 |
|
131 |
+
| 1.3804 | 0.63 | 405 | 1.4009 |
|
132 |
+
| 1.3686 | 0.64 | 410 | 1.4003 |
|
133 |
+
| 1.3975 | 0.64 | 415 | 1.4003 |
|
134 |
+
| 1.3289 | 0.65 | 420 | 1.4000 |
|
135 |
+
| 1.3336 | 0.66 | 425 | 1.3991 |
|
136 |
+
| 1.3958 | 0.67 | 430 | 1.3979 |
|
137 |
+
| 1.2227 | 0.67 | 435 | 1.3972 |
|
138 |
+
| 1.3202 | 0.68 | 440 | 1.3967 |
|
139 |
+
| 1.3508 | 0.69 | 445 | 1.3963 |
|
140 |
+
| 1.4077 | 0.7 | 450 | 1.3956 |
|
141 |
+
| 1.4148 | 0.71 | 455 | 1.3952 |
|
142 |
+
| 1.4219 | 0.71 | 460 | 1.3948 |
|
143 |
+
| 1.3802 | 0.72 | 465 | 1.3949 |
|
144 |
+
| 1.301 | 0.73 | 470 | 1.3945 |
|
145 |
+
| 1.2894 | 0.74 | 475 | 1.3938 |
|
146 |
+
| 1.3469 | 0.74 | 480 | 1.3940 |
|
147 |
+
| 1.2852 | 0.75 | 485 | 1.3941 |
|
148 |
+
| 1.4896 | 0.76 | 490 | 1.3933 |
|
149 |
+
| 1.3953 | 0.77 | 495 | 1.3929 |
|
150 |
+
| 1.3624 | 0.78 | 500 | 1.3926 |
|
151 |
+
| 1.4719 | 0.78 | 505 | 1.3927 |
|
152 |
+
| 1.3274 | 0.79 | 510 | 1.3920 |
|
153 |
+
| 1.2106 | 0.8 | 515 | 1.3917 |
|
154 |
+
| 1.3851 | 0.81 | 520 | 1.3918 |
|
155 |
+
| 1.344 | 0.81 | 525 | 1.3916 |
|
156 |
+
| 1.3197 | 0.82 | 530 | 1.3917 |
|
157 |
+
| 1.3426 | 0.83 | 535 | 1.3922 |
|
158 |
+
| 1.266 | 0.84 | 540 | 1.3919 |
|
159 |
+
| 1.392 | 0.84 | 545 | 1.3918 |
|
160 |
+
| 1.325 | 0.85 | 550 | 1.3918 |
|
161 |
+
| 1.4706 | 0.86 | 555 | 1.3915 |
|
162 |
+
| 1.3695 | 0.87 | 560 | 1.3910 |
|
163 |
+
| 1.4036 | 0.88 | 565 | 1.3912 |
|
164 |
+
| 1.3042 | 0.88 | 570 | 1.3912 |
|
165 |
+
| 1.2578 | 0.89 | 575 | 1.3912 |
|
166 |
+
| 1.3579 | 0.9 | 580 | 1.3915 |
|
167 |
+
| 1.3324 | 0.91 | 585 | 1.3913 |
|
168 |
+
| 1.5166 | 0.91 | 590 | 1.3911 |
|
169 |
+
| 1.3563 | 0.92 | 595 | 1.3907 |
|
170 |
+
| 1.4271 | 0.93 | 600 | 1.3901 |
|
171 |
+
| 1.4084 | 0.94 | 605 | 1.3899 |
|
172 |
+
| 1.3975 | 0.95 | 610 | 1.3897 |
|
173 |
+
| 1.3887 | 0.95 | 615 | 1.3896 |
|
174 |
+
| 1.4221 | 0.96 | 620 | 1.3898 |
|
175 |
+
| 1.4031 | 0.97 | 625 | 1.3898 |
|
176 |
+
| 1.3114 | 0.98 | 630 | 1.3897 |
|
177 |
+
| 1.4907 | 0.98 | 635 | 1.3896 |
|
178 |
+
| 1.3519 | 0.99 | 640 | 1.3898 |
|
179 |
+
| 1.3648 | 1.0 | 645 | 1.3898 |
|
180 |
+
|
181 |
+
|
182 |
+
### Framework versions
|
183 |
+
|
184 |
+
- PEFT 0.7.1
|
185 |
+
- Transformers 4.36.2
|
186 |
+
- Pytorch 2.1.0+cu118
|
187 |
+
- Datasets 2.16.1
|
188 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-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": 16,
|
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": 64,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"w3",
|
23 |
+
"lm_head",
|
24 |
+
"w2",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj",
|
27 |
+
"q_proj",
|
28 |
+
"k_proj",
|
29 |
+
"w1"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM"
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5cb2e1263dc42673c927ca9735f07ab84645b81ec594815419f44130d2a2e0f
|
3 |
+
size 4375780256
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c0055033a2482543ae7542fd2afd6b7f111b7a231104f603892d60f0d9ceee1
|
3 |
+
size 4728
|