Hugging Face's logo

Ludo33
/
e5_RSE_MultiLabel_08092025

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
Ludo33 commited on
Commit
cdcee80
·
verified ·
1 Parent(s): 68fd30b

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -23
  2. model.safetensors +1 -1
  3. runs/Sep10_09-08-15_1b80ce3f2b66/events.out.tfevents.1757495308.1b80ce3f2b66.1333.0 +2 -2
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.2268
20
- - F1 Weighted: 0.8908
21
 
22
  ## Model description
23
 
@@ -44,37 +44,38 @@ The following hyperparameters were used during training:
44
  - total_train_batch_size: 32
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 30
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | F1 Weighted |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
54
- | 1.2037 | 1.0 | 178 | 0.9085 | 0.5503 |
55
- | 1.0769 | 2.0 | 356 | 0.6310 | 0.6213 |
56
- | 0.8062 | 3.0 | 534 | 0.4692 | 0.7237 |
57
- | 0.7147 | 4.0 | 712 | 0.3907 | 0.7807 |
58
- | 0.6277 | 5.0 | 890 | 0.3466 | 0.8033 |
59
- | 0.6465 | 6.0 | 1068 | 0.3208 | 0.8187 |
60
- | 0.5379 | 7.0 | 1246 | 0.3005 | 0.8303 |
61
- | 0.5094 | 8.0 | 1424 | 0.2770 | 0.8453 |
62
- | 0.4985 | 9.0 | 1602 | 0.2618 | 0.8601 |
63
- | 0.4503 | 10.0 | 1780 | 0.2474 | 0.8701 |
64
- | 0.4535 | 11.0 | 1958 | 0.2471 | 0.8728 |
65
- | 0.4743 | 12.0 | 2136 | 0.2383 | 0.8768 |
66
- | 0.4034 | 13.0 | 2314 | 0.2395 | 0.8779 |
67
- | 0.3987 | 14.0 | 2492 | 0.2304 | 0.8839 |
68
- | 0.3973 | 15.0 | 2670 | 0.2309 | 0.8848 |
69
- | 0.362 | 16.0 | 2848 | 0.2229 | 0.8923 |
70
- | 0.3669 | 17.0 | 3026 | 0.2189 | 0.8928 |
71
- | 0.3504 | 18.0 | 3204 | 0.2245 | 0.8905 |
72
- | 0.3982 | 19.0 | 3382 | 0.2268 | 0.8908 |
 
73
 
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.56.0
78
  - Pytorch 2.8.0+cu126
79
  - Datasets 4.0.0
80
  - Tokenizers 0.22.0
 
16
 
17
  This model is a fine-tuned version of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2425
20
+ - F1 Weighted: 0.8843
21
 
22
  ## Model description
23
 
 
44
  - total_train_batch_size: 32
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 20
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | F1 Weighted |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
54
+ | 1.0829 | 1.0 | 178 | 0.8684 | 0.5980 |
55
+ | 0.8123 | 2.0 | 356 | 0.5814 | 0.6966 |
56
+ | 0.6025 | 3.0 | 534 | 0.4584 | 0.7583 |
57
+ | 0.4907 | 4.0 | 712 | 0.3871 | 0.7954 |
58
+ | 0.422 | 5.0 | 890 | 0.3562 | 0.8068 |
59
+ | 0.3762 | 6.0 | 1068 | 0.3218 | 0.8299 |
60
+ | 0.3347 | 7.0 | 1246 | 0.3066 | 0.8399 |
61
+ | 0.3032 | 8.0 | 1424 | 0.2843 | 0.8505 |
62
+ | 0.2782 | 9.0 | 1602 | 0.2726 | 0.8592 |
63
+ | 0.2527 | 10.0 | 1780 | 0.2639 | 0.8653 |
64
+ | 0.2352 | 11.0 | 1958 | 0.2632 | 0.8648 |
65
+ | 0.2211 | 12.0 | 2136 | 0.2549 | 0.8717 |
66
+ | 0.2076 | 13.0 | 2314 | 0.2557 | 0.8746 |
67
+ | 0.1963 | 14.0 | 2492 | 0.2467 | 0.8816 |
68
+ | 0.1865 | 15.0 | 2670 | 0.2471 | 0.8808 |
69
+ | 0.1808 | 16.0 | 2848 | 0.2471 | 0.8829 |
70
+ | 0.1755 | 17.0 | 3026 | 0.2391 | 0.8873 |
71
+ | 0.1723 | 18.0 | 3204 | 0.2404 | 0.8853 |
72
+ | 0.1665 | 19.0 | 3382 | 0.2434 | 0.8848 |
73
+ | 0.1643 | 20.0 | 3560 | 0.2425 | 0.8843 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.56.1
79
  - Pytorch 2.8.0+cu126
80
  - Datasets 4.0.0
81
  - Tokenizers 0.22.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a83771cbd3b1894eca1cc42dbf8a537f9daeff21e7871531147e362576ffa407
3
  size 2239659672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d9fa382e87804a8d755f2a51a73b11bd6d2fb8e4869685de948d0e2341163a
3
  size 2239659672
runs/Sep10_09-08-15_1b80ce3f2b66/events.out.tfevents.1757495308.1b80ce3f2b66.1333.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91c3337f06abff00a49cdaf615507f61b04b4c72fb8d88a621551e0aac57098a
3
- size 16789
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315df4d7a24ad327890c13e749f5581c3c3cd8421721024d770c13a96733e142
3
+ size 17143