Hugging Face's logo

stulcrad
/
XLM-RoBERTa-2

Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
f7a3f22
·
verified ·
1 Parent(s): 52706da

End of training

Browse files
Files changed (7) hide show
  1. README.md +16 -16
  2. config.json +2 -2
  3. model.safetensors +1 -1
  4. runs/Feb23_16-22-54_dgx10/events.out.tfevents.1740324187.dgx10.4171446.0 +3 -0
  5. runs/Feb23_16-33-39_dgx10/events.out.tfevents.1740324822.dgx10.4171446.1 +3 -0
  6. runs/Feb23_16-33-39_dgx10/events.out.tfevents.1740366134.dgx10.4171446.2 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -20,14 +20,14 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4441
24
- - Accuracy: 0.9035
25
- - Micro Precision: 0.9035
26
- - Micro Recall: 0.9035
27
- - Micro F1: 0.9035
28
- - Macro Precision: 0.8681
29
- - Macro Recall: 0.8564
30
- - Macro F1: 0.8581
31
 
32
  ## Model description
33
 
@@ -61,14 +61,14 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 |
63
  |:-------------:|:-----:|:------:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|
64
- | 0.506 | 1.0 | 15074 | 0.4465 | 0.8717 | 0.8717 | 0.8717 | 0.8717 | 0.8315 | 0.8249 | 0.8189 |
65
- | 0.4444 | 2.0 | 30148 | 0.4104 | 0.8797 | 0.8797 | 0.8797 | 0.8797 | 0.8369 | 0.8384 | 0.8268 |
66
- | 0.347 | 3.0 | 45222 | 0.3999 | 0.8918 | 0.8918 | 0.8918 | 0.8918 | 0.8593 | 0.8470 | 0.8458 |
67
- | 0.3004 | 4.0 | 60296 | 0.3732 | 0.8989 | 0.8989 | 0.8989 | 0.8989 | 0.8569 | 0.8628 | 0.8552 |
68
- | 0.2735 | 5.0 | 75370 | 0.3913 | 0.9013 | 0.9013 | 0.9013 | 0.9013 | 0.8596 | 0.8643 | 0.8569 |
69
- | 0.2294 | 6.0 | 90444 | 0.4118 | 0.9035 | 0.9035 | 0.9035 | 0.9035 | 0.8647 | 0.8730 | 0.8643 |
70
- | 0.187 | 7.0 | 105518 | 0.4153 | 0.9051 | 0.9051 | 0.9051 | 0.9051 | 0.8703 | 0.8743 | 0.8680 |
71
- | 0.172 | 8.0 | 120592 | 0.4362 | 0.9048 | 0.9048 | 0.9048 | 0.9048 | 0.8653 | 0.8723 | 0.8637 |
72
 
73
 
74
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6614
24
+ - Accuracy: 0.9100
25
+ - Micro Precision: 0.9100
26
+ - Micro Recall: 0.9100
27
+ - Micro F1: 0.9100
28
+ - Macro Precision: 0.8823
29
+ - Macro Recall: 0.8656
30
+ - Macro F1: 0.8703
31
 
32
  ## Model description
33
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 |
63
  |:-------------:|:-----:|:------:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|
64
+ | 0.4142 | 1.0 | 15074 | 0.3827 | 0.8873 | 0.8873 | 0.8873 | 0.8873 | 0.8729 | 0.8334 | 0.8429 |
65
+ | 0.3407 | 2.0 | 30148 | 0.3548 | 0.8965 | 0.8965 | 0.8965 | 0.8965 | 0.8663 | 0.8600 | 0.8586 |
66
+ | 0.2327 | 3.0 | 45222 | 0.3800 | 0.9015 | 0.9015 | 0.9015 | 0.9015 | 0.8816 | 0.8550 | 0.8623 |
67
+ | 0.1701 | 4.0 | 60296 | 0.4035 | 0.9062 | 0.9062 | 0.9062 | 0.9062 | 0.8730 | 0.8707 | 0.8684 |
68
+ | 0.1281 | 5.0 | 75370 | 0.4522 | 0.9109 | 0.9109 | 0.9109 | 0.9109 | 0.8751 | 0.8833 | 0.8755 |
69
+ | 0.1007 | 6.0 | 90444 | 0.5409 | 0.9109 | 0.9109 | 0.9109 | 0.9109 | 0.8741 | 0.8776 | 0.8723 |
70
+ | 0.0598 | 7.0 | 105518 | 0.5965 | 0.9115 | 0.9115 | 0.9115 | 0.9115 | 0.8773 | 0.8803 | 0.8751 |
71
+ | 0.0519 | 8.0 | 120592 | 0.6388 | 0.9131 | 0.9131 | 0.9131 | 0.9131 | 0.8736 | 0.8817 | 0.8738 |
72
 
73
 
74
  ### Framework versions
config.json CHANGED
@@ -3,12 +3,12 @@
3
  "architectures": [
4
  "RelationExtractionModel"
5
  ],
6
- "attention_probs_dropout_prob": 0.25,
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.25,
12
  "hidden_size": 1024,
13
  "id2label": {
14
  "0": "P0 other",
 
3
  "architectures": [
4
  "RelationExtractionModel"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
  "hidden_size": 1024,
13
  "id2label": {
14
  "0": "P0 other",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:263ed6385608569ac4c500dd907e5be45793f820784b0733c36ec8fc886dd32f
3
  size 2240416848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed12f364660765f2470d20feaf19e2103a3bd41d4ce62f125489e8ed1951dd7
3
  size 2240416848
runs/Feb23_16-22-54_dgx10/events.out.tfevents.1740324187.dgx10.4171446.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d484c536cb07053e5b4c30adecb67acec8f6498e2ddc07d783ff08c948f5d6
3
+ size 10718
runs/Feb23_16-33-39_dgx10/events.out.tfevents.1740324822.dgx10.4171446.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b8d63aa71c5022bd24016090246ad90f736b9d172a5f671513523f5dfad20d
3
+ size 67238
runs/Feb23_16-33-39_dgx10/events.out.tfevents.1740366134.dgx10.4171446.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce362229c2976044013002cb440c66e42ab14a5809228e03462689c76f416a76
3
+ size 757
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b873ac0ed7c7180499ed7d0365eda1bcfba9f27ad41b0f08c7fbd9d29f25c37b
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304663f5f22a482e5f26a27058b5ec70058f0998a6ee6e274b1ea399fcde2625
3
  size 5304