Hugging Face's logo

Acadys
/
PointCon-Mixtral

PEFT
Safetensors
Generated from Trainer
Model card Files Community
IUseAMouse commited on
Commit
0f239a8
•
1 Parent(s): 5eee000

End of training

Browse files
Files changed (4) hide show
  1. README.md +188 -0
  2. adapter_config.json +32 -0
  3. adapter_model.safetensors +3 -0
  4. 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