Hugging Face's logo

allen0909
/
ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V5

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
allen0909 commited on
Commit
e7f09d0
•
1 Parent(s): 9627995

End of training

Browse files
Files changed (2) hide show
  1. README.md +65 -127
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -7,18 +7,18 @@ tags:
7
  - generated_from_trainer
8
  base_model: taide/TAIDE-LX-7B-Chat
9
  model-index:
10
- - name: ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V4
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
- # ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V4
18
 
19
  This model is a fine-tuned version of [taide/TAIDE-LX-7B-Chat](https://huggingface.co/taide/TAIDE-LX-7B-Chat) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3344
22
 
23
  ## Model description
24
 
@@ -51,130 +51,68 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:------:|:-----:|:---------------:|
56
- | 4.8611 | 0.0321 | 100 | 3.4673 |
57
- | 4.6379 | 0.0643 | 200 | 3.2251 |
58
- | 3.817 | 0.0964 | 300 | 2.8123 |
59
- | 3.2954 | 0.1285 | 400 | 2.4988 |
60
- | 2.9281 | 0.1607 | 500 | 2.2574 |
61
- | 2.2501 | 0.1928 | 600 | 1.9403 |
62
- | 2.1188 | 0.2249 | 700 | 1.7765 |
63
- | 1.8027 | 0.2571 | 800 | 1.6201 |
64
- | 1.6638 | 0.2892 | 900 | 1.4923 |
65
- | 1.6204 | 0.3213 | 1000 | 1.3941 |
66
- | 1.6152 | 0.3535 | 1100 | 1.2081 |
67
- | 1.0876 | 0.3856 | 1200 | 1.0603 |
68
- | 1.2552 | 0.4177 | 1300 | 1.0356 |
69
- | 0.9443 | 0.4499 | 1400 | 0.8980 |
70
- | 0.9998 | 0.4820 | 1500 | 0.8488 |
71
- | 1.0518 | 0.5141 | 1600 | 0.7801 |
72
- | 0.984 | 0.5463 | 1700 | 0.7711 |
73
- | 0.9595 | 0.5784 | 1800 | 0.6924 |
74
- | 0.9363 | 0.6105 | 1900 | 0.6537 |
75
- | 0.822 | 0.6427 | 2000 | 0.6399 |
76
- | 0.8791 | 0.6748 | 2100 | 0.6050 |
77
- | 0.8802 | 0.7069 | 2200 | 0.5914 |
78
- | 0.788 | 0.7391 | 2300 | 0.5741 |
79
- | 0.7853 | 0.7712 | 2400 | 0.5581 |
80
- | 0.839 | 0.8033 | 2500 | 0.5398 |
81
- | 0.847 | 0.8355 | 2600 | 0.5204 |
82
- | 0.8446 | 0.8676 | 2700 | 0.5085 |
83
- | 0.7599 | 0.8997 | 2800 | 0.4867 |
84
- | 0.7602 | 0.9319 | 2900 | 0.4891 |
85
- | 0.8813 | 0.9640 | 3000 | 0.4717 |
86
- | 0.6966 | 0.9961 | 3100 | 0.4667 |
87
- | 0.7106 | 1.0283 | 3200 | 0.4463 |
88
- | 0.6553 | 1.0604 | 3300 | 0.4414 |
89
- | 0.6721 | 1.0925 | 3400 | 0.4383 |
90
- | 0.6625 | 1.1247 | 3500 | 0.4326 |
91
- | 0.6458 | 1.1568 | 3600 | 0.4255 |
92
- | 0.6491 | 1.1889 | 3700 | 0.4207 |
93
- | 0.6773 | 1.2211 | 3800 | 0.4246 |
94
- | 0.6972 | 1.2532 | 3900 | 0.4119 |
95
- | 0.7315 | 1.2853 | 4000 | 0.4101 |
96
- | 0.6167 | 1.3175 | 4100 | 0.4119 |
97
- | 0.6052 | 1.3496 | 4200 | 0.4070 |
98
- | 0.6168 | 1.3817 | 4300 | 0.4029 |
99
- | 0.6283 | 1.4139 | 4400 | 0.3986 |
100
- | 0.6434 | 1.4460 | 4500 | 0.3940 |
101
- | 0.6244 | 1.4781 | 4600 | 0.3940 |
102
- | 0.6385 | 1.5103 | 4700 | 0.3958 |
103
- | 0.6577 | 1.5424 | 4800 | 0.3952 |
104
- | 0.6616 | 1.5746 | 4900 | 0.3925 |
105
- | 0.6295 | 1.6067 | 5000 | 0.3846 |
106
- | 0.6327 | 1.6388 | 5100 | 0.3832 |
107
- | 0.6539 | 1.6710 | 5200 | 0.3826 |
108
- | 0.6291 | 1.7031 | 5300 | 0.3851 |
109
- | 0.5879 | 1.7352 | 5400 | 0.3833 |
110
- | 0.6002 | 1.7674 | 5500 | 0.3787 |
111
- | 0.5673 | 1.7995 | 5600 | 0.3755 |
112
- | 0.5956 | 1.8316 | 5700 | 0.3746 |
113
- | 0.6186 | 1.8638 | 5800 | 0.3735 |
114
- | 0.5756 | 1.8959 | 5900 | 0.3712 |
115
- | 0.6281 | 1.9280 | 6000 | 0.3735 |
116
- | 0.5736 | 1.9602 | 6100 | 0.3696 |
117
- | 0.5762 | 1.9923 | 6200 | 0.3700 |
118
- | 0.3585 | 2.0244 | 6300 | 0.3667 |
119
- | 0.4526 | 2.0566 | 6400 | 0.3662 |
120
- | 0.3883 | 2.0887 | 6500 | 0.3662 |
121
- | 0.4083 | 2.1208 | 6600 | 0.3664 |
122
- | 0.3973 | 2.1530 | 6700 | 0.3646 |
123
- | 0.4206 | 2.1851 | 6800 | 0.3673 |
124
- | 0.5028 | 2.2172 | 6900 | 0.3622 |
125
- | 0.366 | 2.2494 | 7000 | 0.3629 |
126
- | 0.3968 | 2.2815 | 7100 | 0.3620 |
127
- | 0.3977 | 2.3136 | 7200 | 0.3582 |
128
- | 0.3899 | 2.3458 | 7300 | 0.3583 |
129
- | 0.393 | 2.3779 | 7400 | 0.3572 |
130
- | 0.4467 | 2.4100 | 7500 | 0.3576 |
131
- | 0.4327 | 2.4422 | 7600 | 0.3605 |
132
- | 0.4128 | 2.4743 | 7700 | 0.3550 |
133
- | 0.3888 | 2.5064 | 7800 | 0.3572 |
134
- | 0.4373 | 2.5386 | 7900 | 0.3553 |
135
- | 0.3817 | 2.5707 | 8000 | 0.3525 |
136
- | 0.3852 | 2.6028 | 8100 | 0.3518 |
137
- | 0.4573 | 2.6350 | 8200 | 0.3536 |
138
- | 0.3833 | 2.6671 | 8300 | 0.3499 |
139
- | 0.3731 | 2.6992 | 8400 | 0.3509 |
140
- | 0.3867 | 2.7314 | 8500 | 0.3497 |
141
- | 0.351 | 2.7635 | 8600 | 0.3475 |
142
- | 0.4327 | 2.7956 | 8700 | 0.3485 |
143
- | 0.4183 | 2.8278 | 8800 | 0.3478 |
144
- | 0.3807 | 2.8599 | 8900 | 0.3488 |
145
- | 0.397 | 2.8920 | 9000 | 0.3461 |
146
- | 0.4218 | 2.9242 | 9100 | 0.3463 |
147
- | 0.3684 | 2.9563 | 9200 | 0.3457 |
148
- | 0.3992 | 2.9884 | 9300 | 0.3448 |
149
- | 0.2395 | 3.0206 | 9400 | 0.3463 |
150
- | 0.2221 | 3.0527 | 9500 | 0.3448 |
151
- | 0.222 | 3.0848 | 9600 | 0.3451 |
152
- | 0.2359 | 3.1170 | 9700 | 0.3439 |
153
- | 0.227 | 3.1491 | 9800 | 0.3442 |
154
- | 0.2083 | 3.1812 | 9900 | 0.3430 |
155
- | 0.2141 | 3.2134 | 10000 | 0.3419 |
156
- | 0.224 | 3.2455 | 10100 | 0.3429 |
157
- | 0.2031 | 3.2776 | 10200 | 0.3420 |
158
- | 0.1944 | 3.3098 | 10300 | 0.3414 |
159
- | 0.2109 | 3.3419 | 10400 | 0.3397 |
160
- | 0.2053 | 3.3740 | 10500 | 0.3412 |
161
- | 0.2172 | 3.4062 | 10600 | 0.3398 |
162
- | 0.2179 | 3.4383 | 10700 | 0.3385 |
163
- | 0.2299 | 3.4704 | 10800 | 0.3383 |
164
- | 0.1721 | 3.5026 | 10900 | 0.3389 |
165
- | 0.2131 | 3.5347 | 11000 | 0.3387 |
166
- | 0.2489 | 3.5668 | 11100 | 0.3376 |
167
- | 0.224 | 3.5990 | 11200 | 0.3373 |
168
- | 0.201 | 3.6311 | 11300 | 0.3370 |
169
- | 0.2131 | 3.6632 | 11400 | 0.3364 |
170
- | 0.1869 | 3.6954 | 11500 | 0.3369 |
171
- | 0.2174 | 3.7275 | 11600 | 0.3358 |
172
- | 0.1999 | 3.7596 | 11700 | 0.3355 |
173
- | 0.2224 | 3.7918 | 11800 | 0.3352 |
174
- | 0.2195 | 3.8239 | 11900 | 0.3346 |
175
- | 0.1984 | 3.8560 | 12000 | 0.3344 |
176
- | 0.2121 | 3.8882 | 12100 | 0.3337 |
177
- | 0.1879 | 3.9203 | 12200 | 0.3344 |
178
 
179
 
180
  ### Framework versions
 
7
  - generated_from_trainer
8
  base_model: taide/TAIDE-LX-7B-Chat
9
  model-index:
10
+ - name: ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V5
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
+ # ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V5
18
 
19
  This model is a fine-tuned version of [taide/TAIDE-LX-7B-Chat](https://huggingface.co/taide/TAIDE-LX-7B-Chat) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3726
22
 
23
  ## Model description
24
 
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 4.8629 | 0.0321 | 100 | 3.4698 |
57
+ | 4.6474 | 0.0643 | 200 | 3.2343 |
58
+ | 3.8261 | 0.0964 | 300 | 2.8205 |
59
+ | 3.2992 | 0.1285 | 400 | 2.5034 |
60
+ | 2.9369 | 0.1607 | 500 | 2.2639 |
61
+ | 2.2674 | 0.1928 | 600 | 1.9493 |
62
+ | 2.1393 | 0.2249 | 700 | 1.7888 |
63
+ | 1.8195 | 0.2571 | 800 | 1.6285 |
64
+ | 1.678 | 0.2892 | 900 | 1.4983 |
65
+ | 1.6242 | 0.3213 | 1000 | 1.4013 |
66
+ | 1.344 | 0.3535 | 1100 | 1.1522 |
67
+ | 1.0894 | 0.3856 | 1200 | 1.0704 |
68
+ | 1.2033 | 0.4177 | 1300 | 1.0537 |
69
+ | 0.9503 | 0.4499 | 1400 | 0.9160 |
70
+ | 0.9901 | 0.4820 | 1500 | 0.8751 |
71
+ | 1.0363 | 0.5141 | 1600 | 0.7942 |
72
+ | 0.9986 | 0.5463 | 1700 | 0.7668 |
73
+ | 0.9407 | 0.5784 | 1800 | 0.6912 |
74
+ | 0.9347 | 0.6105 | 1900 | 0.6543 |
75
+ | 0.8109 | 0.6427 | 2000 | 0.6498 |
76
+ | 0.8848 | 0.6748 | 2100 | 0.6077 |
77
+ | 0.8937 | 0.7069 | 2200 | 0.5865 |
78
+ | 0.7895 | 0.7391 | 2300 | 0.5780 |
79
+ | 0.8044 | 0.7712 | 2400 | 0.5646 |
80
+ | 0.8317 | 0.8033 | 2500 | 0.5449 |
81
+ | 0.858 | 0.8355 | 2600 | 0.5132 |
82
+ | 0.8519 | 0.8676 | 2700 | 0.4940 |
83
+ | 0.7554 | 0.8997 | 2800 | 0.4972 |
84
+ | 0.758 | 0.9319 | 2900 | 0.4809 |
85
+ | 0.8866 | 0.9640 | 3000 | 0.4714 |
86
+ | 0.7028 | 0.9961 | 3100 | 0.4608 |
87
+ | 0.7031 | 1.0283 | 3200 | 0.4458 |
88
+ | 0.6623 | 1.0604 | 3300 | 0.4427 |
89
+ | 0.671 | 1.0925 | 3400 | 0.4366 |
90
+ | 0.6588 | 1.1247 | 3500 | 0.4327 |
91
+ | 0.6422 | 1.1568 | 3600 | 0.4239 |
92
+ | 0.643 | 1.1889 | 3700 | 0.4235 |
93
+ | 0.6747 | 1.2211 | 3800 | 0.4204 |
94
+ | 0.6911 | 1.2532 | 3900 | 0.4130 |
95
+ | 0.7354 | 1.2853 | 4000 | 0.4092 |
96
+ | 0.6233 | 1.3175 | 4100 | 0.4070 |
97
+ | 0.6005 | 1.3496 | 4200 | 0.4055 |
98
+ | 0.624 | 1.3817 | 4300 | 0.4033 |
99
+ | 0.623 | 1.4139 | 4400 | 0.3976 |
100
+ | 0.6419 | 1.4460 | 4500 | 0.3966 |
101
+ | 0.6329 | 1.4781 | 4600 | 0.3914 |
102
+ | 0.6395 | 1.5103 | 4700 | 0.3934 |
103
+ | 0.6541 | 1.5424 | 4800 | 0.3916 |
104
+ | 0.6538 | 1.5746 | 4900 | 0.3917 |
105
+ | 0.6214 | 1.6067 | 5000 | 0.3840 |
106
+ | 0.6303 | 1.6388 | 5100 | 0.3844 |
107
+ | 0.6547 | 1.6710 | 5200 | 0.3816 |
108
+ | 0.6264 | 1.7031 | 5300 | 0.3844 |
109
+ | 0.5896 | 1.7352 | 5400 | 0.3801 |
110
+ | 0.6082 | 1.7674 | 5500 | 0.3786 |
111
+ | 0.5772 | 1.7995 | 5600 | 0.3737 |
112
+ | 0.5839 | 1.8316 | 5700 | 0.3745 |
113
+ | 0.6201 | 1.8638 | 5800 | 0.3737 |
114
+ | 0.5643 | 1.8959 | 5900 | 0.3717 |
115
+ | 0.6258 | 1.9280 | 6000 | 0.3726 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
 
117
 
118
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983a410797727eaf6ef6c08a8ac79809f2e8a36bd84dde01c4e9bce24b2dddc1
3
  size 16794200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af56bc9a8bdac6a601007449182fd057f505da19405156c151286b9d23e2f7e7
3
  size 16794200