Hugging Face's logo

gentilrenard
/
multi-e5-base_lmd-comments_v1

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
gentilrenard commited on
Commit
8ab0514
•
1 Parent(s): 1eecfc5

multi-e5-base_lmd-comments_v1

Browse files
Files changed (3) hide show
  1. README.md +53 -53
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # multi-e5-base_lmd-comments_v1
18
 
19
- This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6013
22
- - F1: 0.8539
23
- - Accuracy: 0.8505
24
 
25
  ## Model description
26
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: cosine
48
  - lr_scheduler_warmup_ratio: 0.1
49
  - num_epochs: 2
50
 
@@ -52,54 +52,54 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
55
- | 1.0859 | 0.04 | 100 | 1.0531 | 0.6574 | 0.6716 |
56
- | 0.9993 | 0.08 | 200 | 0.8669 | 0.7260 | 0.7266 |
57
- | 0.7514 | 0.12 | 300 | 0.7077 | 0.7582 | 0.7699 |
58
- | 0.6928 | 0.17 | 400 | 0.8825 | 0.7521 | 0.7856 |
59
- | 0.6349 | 0.21 | 500 | 0.6178 | 0.7947 | 0.7778 |
60
- | 0.5939 | 0.25 | 600 | 0.6509 | 0.7977 | 0.7847 |
61
- | 0.6461 | 0.29 | 700 | 0.5820 | 0.7951 | 0.7778 |
62
- | 0.5346 | 0.33 | 800 | 0.7509 | 0.8022 | 0.8014 |
63
- | 0.622 | 0.37 | 900 | 0.8165 | 0.7902 | 0.7935 |
64
- | 0.6124 | 0.41 | 1000 | 0.6754 | 0.7885 | 0.7788 |
65
- | 0.6285 | 0.46 | 1100 | 0.5179 | 0.8284 | 0.8210 |
66
- | 0.5838 | 0.5 | 1200 | 0.5335 | 0.8149 | 0.8024 |
67
- | 0.6116 | 0.54 | 1300 | 0.5584 | 0.8301 | 0.8240 |
68
- | 0.5578 | 0.58 | 1400 | 0.6135 | 0.7670 | 0.7404 |
69
- | 0.534 | 0.62 | 1500 | 0.6407 | 0.8153 | 0.8063 |
70
- | 0.5343 | 0.66 | 1600 | 0.5500 | 0.8381 | 0.8279 |
71
- | 0.5575 | 0.7 | 1700 | 0.6355 | 0.8170 | 0.8102 |
72
- | 0.5961 | 0.75 | 1800 | 0.5465 | 0.8450 | 0.8446 |
73
- | 0.5623 | 0.79 | 1900 | 0.5787 | 0.7875 | 0.7719 |
74
- | 0.5436 | 0.83 | 2000 | 0.6035 | 0.8494 | 0.8525 |
75
- | 0.5662 | 0.87 | 2100 | 0.4979 | 0.8210 | 0.8083 |
76
- | 0.5227 | 0.91 | 2200 | 0.6157 | 0.8320 | 0.8328 |
77
- | 0.557 | 0.95 | 2300 | 0.5721 | 0.8488 | 0.8505 |
78
- | 0.5369 | 0.99 | 2400 | 0.5191 | 0.8222 | 0.8112 |
79
- | 0.4846 | 1.04 | 2500 | 0.4966 | 0.8304 | 0.8201 |
80
- | 0.4094 | 1.08 | 2600 | 0.6385 | 0.8368 | 0.8328 |
81
- | 0.4045 | 1.12 | 2700 | 0.6165 | 0.8476 | 0.8456 |
82
- | 0.4835 | 1.16 | 2800 | 0.6792 | 0.8536 | 0.8535 |
83
- | 0.3949 | 1.2 | 2900 | 0.7400 | 0.8559 | 0.8574 |
84
- | 0.4157 | 1.24 | 3000 | 0.6305 | 0.8319 | 0.8279 |
85
- | 0.4638 | 1.28 | 3100 | 0.5507 | 0.8438 | 0.8387 |
86
- | 0.4438 | 1.33 | 3200 | 0.5208 | 0.8426 | 0.8348 |
87
- | 0.4224 | 1.37 | 3300 | 0.6534 | 0.8330 | 0.8279 |
88
- | 0.4703 | 1.41 | 3400 | 0.6486 | 0.8456 | 0.8427 |
89
- | 0.4912 | 1.45 | 3500 | 0.6370 | 0.8544 | 0.8505 |
90
- | 0.4396 | 1.49 | 3600 | 0.6866 | 0.8520 | 0.8505 |
91
- | 0.437 | 1.53 | 3700 | 0.6436 | 0.8536 | 0.8505 |
92
- | 0.3993 | 1.57 | 3800 | 0.6910 | 0.8517 | 0.8515 |
93
- | 0.3712 | 1.62 | 3900 | 0.6449 | 0.8588 | 0.8564 |
94
- | 0.4156 | 1.66 | 4000 | 0.6478 | 0.8560 | 0.8535 |
95
- | 0.4564 | 1.7 | 4100 | 0.6475 | 0.8577 | 0.8555 |
96
- | 0.4273 | 1.74 | 4200 | 0.6044 | 0.8456 | 0.8397 |
97
- | 0.4284 | 1.78 | 4300 | 0.6219 | 0.8499 | 0.8466 |
98
- | 0.4466 | 1.82 | 4400 | 0.5871 | 0.8535 | 0.8496 |
99
- | 0.3932 | 1.86 | 4500 | 0.5940 | 0.8551 | 0.8515 |
100
- | 0.3848 | 1.91 | 4600 | 0.5995 | 0.8559 | 0.8525 |
101
- | 0.4337 | 1.95 | 4700 | 0.6023 | 0.8539 | 0.8505 |
102
- | 0.3991 | 1.99 | 4800 | 0.6013 | 0.8539 | 0.8505 |
103
 
104
 
105
  ### Framework versions
 
16
 
17
  # multi-e5-base_lmd-comments_v1
18
 
19
+ This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.1145
22
+ - F1: 0.7338
23
+ - Accuracy: 0.7410
24
 
25
  ## Model description
26
 
 
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
  - num_epochs: 2
50
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
55
+ | 1.1179 | 0.04 | 100 | 1.1781 | 0.3969 | 0.4748 |
56
+ | 1.0342 | 0.08 | 200 | 1.0924 | 0.5137 | 0.5899 |
57
+ | 0.7423 | 0.12 | 300 | 0.9700 | 0.6454 | 0.6691 |
58
+ | 0.7046 | 0.17 | 400 | 0.8990 | 0.6462 | 0.6691 |
59
+ | 0.6419 | 0.21 | 500 | 0.9583 | 0.6220 | 0.6475 |
60
+ | 0.6679 | 0.25 | 600 | 0.8621 | 0.6757 | 0.6835 |
61
+ | 0.6244 | 0.29 | 700 | 0.8017 | 0.7399 | 0.7410 |
62
+ | 0.5747 | 0.33 | 800 | 0.8040 | 0.6950 | 0.6906 |
63
+ | 0.5575 | 0.37 | 900 | 1.1045 | 0.6774 | 0.6906 |
64
+ | 0.5994 | 0.41 | 1000 | 1.1592 | 0.6725 | 0.6978 |
65
+ | 0.5565 | 0.46 | 1100 | 0.9960 | 0.7303 | 0.7338 |
66
+ | 0.511 | 0.5 | 1200 | 1.0861 | 0.7377 | 0.7482 |
67
+ | 0.5448 | 0.54 | 1300 | 0.7945 | 0.7155 | 0.7122 |
68
+ | 0.6059 | 0.58 | 1400 | 0.8167 | 0.6879 | 0.6906 |
69
+ | 0.4865 | 0.62 | 1500 | 1.1002 | 0.7181 | 0.7266 |
70
+ | 0.566 | 0.66 | 1600 | 0.7388 | 0.6678 | 0.6691 |
71
+ | 0.4756 | 0.7 | 1700 | 1.1751 | 0.7385 | 0.7482 |
72
+ | 0.5595 | 0.75 | 1800 | 1.0169 | 0.7204 | 0.7266 |
73
+ | 0.5838 | 0.79 | 1900 | 0.7718 | 0.7005 | 0.6978 |
74
+ | 0.573 | 0.83 | 2000 | 0.9156 | 0.7174 | 0.7266 |
75
+ | 0.5623 | 0.87 | 2100 | 0.8405 | 0.7416 | 0.7482 |
76
+ | 0.4929 | 0.91 | 2200 | 0.8329 | 0.7484 | 0.7554 |
77
+ | 0.5135 | 0.95 | 2300 | 1.1845 | 0.7008 | 0.7194 |
78
+ | 0.5217 | 0.99 | 2400 | 1.1482 | 0.7204 | 0.7338 |
79
+ | 0.4342 | 1.04 | 2500 | 1.3326 | 0.7078 | 0.7266 |
80
+ | 0.4975 | 1.08 | 2600 | 1.0527 | 0.7048 | 0.7194 |
81
+ | 0.4135 | 1.12 | 2700 | 0.9742 | 0.7431 | 0.7482 |
82
+ | 0.3562 | 1.16 | 2800 | 1.0554 | 0.7359 | 0.7410 |
83
+ | 0.3892 | 1.2 | 2900 | 1.1289 | 0.7403 | 0.7482 |
84
+ | 0.5041 | 1.24 | 3000 | 0.9690 | 0.7642 | 0.7698 |
85
+ | 0.4808 | 1.28 | 3100 | 0.9745 | 0.7378 | 0.7410 |
86
+ | 0.3532 | 1.33 | 3200 | 1.0141 | 0.7521 | 0.7554 |
87
+ | 0.4679 | 1.37 | 3300 | 0.9923 | 0.7410 | 0.7482 |
88
+ | 0.432 | 1.41 | 3400 | 1.0650 | 0.7486 | 0.7554 |
89
+ | 0.4543 | 1.45 | 3500 | 1.1235 | 0.7474 | 0.7554 |
90
+ | 0.4716 | 1.49 | 3600 | 1.0688 | 0.7316 | 0.7410 |
91
+ | 0.4251 | 1.53 | 3700 | 1.0290 | 0.7415 | 0.7482 |
92
+ | 0.3676 | 1.57 | 3800 | 1.1651 | 0.7546 | 0.7626 |
93
+ | 0.4031 | 1.62 | 3900 | 0.9981 | 0.7559 | 0.7626 |
94
+ | 0.4356 | 1.66 | 4000 | 0.9815 | 0.7558 | 0.7626 |
95
+ | 0.4355 | 1.7 | 4100 | 1.0349 | 0.7443 | 0.7482 |
96
+ | 0.4113 | 1.74 | 4200 | 1.1226 | 0.7333 | 0.7410 |
97
+ | 0.4447 | 1.78 | 4300 | 0.9854 | 0.7423 | 0.7482 |
98
+ | 0.4601 | 1.82 | 4400 | 1.0193 | 0.7348 | 0.7410 |
99
+ | 0.4474 | 1.86 | 4500 | 1.0177 | 0.7423 | 0.7482 |
100
+ | 0.3585 | 1.91 | 4600 | 1.0460 | 0.7276 | 0.7338 |
101
+ | 0.4064 | 1.95 | 4700 | 1.0995 | 0.7276 | 0.7338 |
102
+ | 0.4443 | 1.99 | 4800 | 1.1145 | 0.7338 | 0.7410 |
103
 
104
 
105
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6364629546595aa3154bf00cad69cdfd0695fe06f0f6e72c3234fa050e97e6d
3
  size 1112208084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57356c481c5991f26dc38bb95c25e46fc55007d22a6611e4bbff9f94e0fa228
3
  size 1112208084
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5baf6e7361b584742f64641e8a8cbf2b3e1ce1ca4c06a115bfdde6113d7e11a4
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e48c2b142acdd14e0f2b5de550ca41b7b4db814264e512d013f219ac02c529
3
  size 4856