End of training
Browse files- README.md +107 -0
- config.json +29 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: FacebookAI/xlm-roberta-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: XMLRoberta_70KURL
|
| 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 |
+
# XMLRoberta_70KURL
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0047
|
| 22 |
+
- Accuracy: 0.9983
|
| 23 |
+
- F1: 0.9983
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 64
|
| 44 |
+
- eval_batch_size: 64
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 128
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 2150
|
| 51 |
+
- num_epochs: 20
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
|
| 57 |
+
| No log | 0.4651 | 200 | 0.4939 | 0.6704 | 0.5381 |
|
| 58 |
+
| No log | 0.9302 | 400 | 0.2605 | 0.9039 | 0.9028 |
|
| 59 |
+
| No log | 1.3953 | 600 | 0.2110 | 0.9241 | 0.9236 |
|
| 60 |
+
| No log | 1.8605 | 800 | 0.1589 | 0.9422 | 0.9425 |
|
| 61 |
+
| 0.3715 | 2.3256 | 1000 | 0.1458 | 0.9488 | 0.9489 |
|
| 62 |
+
| 0.3715 | 2.7907 | 1200 | 0.1282 | 0.9549 | 0.9549 |
|
| 63 |
+
| 0.3715 | 3.2558 | 1400 | 0.1106 | 0.9616 | 0.9616 |
|
| 64 |
+
| 0.3715 | 3.7209 | 1600 | 0.1033 | 0.9650 | 0.9651 |
|
| 65 |
+
| 0.1516 | 4.1860 | 1800 | 0.0973 | 0.9657 | 0.9657 |
|
| 66 |
+
| 0.1516 | 4.6512 | 2000 | 0.0872 | 0.9706 | 0.9708 |
|
| 67 |
+
| 0.1516 | 5.1163 | 2200 | 0.0743 | 0.9740 | 0.9741 |
|
| 68 |
+
| 0.1516 | 5.5814 | 2400 | 0.0702 | 0.9759 | 0.9760 |
|
| 69 |
+
| 0.1056 | 6.0465 | 2600 | 0.0651 | 0.9780 | 0.9781 |
|
| 70 |
+
| 0.1056 | 6.5116 | 2800 | 0.0565 | 0.9805 | 0.9806 |
|
| 71 |
+
| 0.1056 | 6.9767 | 3000 | 0.0550 | 0.9804 | 0.9805 |
|
| 72 |
+
| 0.1056 | 7.4419 | 3200 | 0.0516 | 0.9837 | 0.9837 |
|
| 73 |
+
| 0.1056 | 7.9070 | 3400 | 0.0649 | 0.9782 | 0.9784 |
|
| 74 |
+
| 0.0776 | 8.3721 | 3600 | 0.0371 | 0.9878 | 0.9878 |
|
| 75 |
+
| 0.0776 | 8.8372 | 3800 | 0.0333 | 0.9887 | 0.9887 |
|
| 76 |
+
| 0.0776 | 9.3023 | 4000 | 0.0317 | 0.9895 | 0.9895 |
|
| 77 |
+
| 0.0776 | 9.7674 | 4200 | 0.0296 | 0.9899 | 0.9900 |
|
| 78 |
+
| 0.0581 | 10.2326 | 4400 | 0.0259 | 0.9919 | 0.9919 |
|
| 79 |
+
| 0.0581 | 10.6977 | 4600 | 0.0235 | 0.9923 | 0.9923 |
|
| 80 |
+
| 0.0581 | 11.1628 | 4800 | 0.0204 | 0.9929 | 0.9929 |
|
| 81 |
+
| 0.0581 | 11.6279 | 5000 | 0.0172 | 0.9941 | 0.9941 |
|
| 82 |
+
| 0.042 | 12.0930 | 5200 | 0.0219 | 0.9929 | 0.9929 |
|
| 83 |
+
| 0.042 | 12.5581 | 5400 | 0.0147 | 0.9953 | 0.9953 |
|
| 84 |
+
| 0.042 | 13.0233 | 5600 | 0.0141 | 0.9952 | 0.9952 |
|
| 85 |
+
| 0.042 | 13.4884 | 5800 | 0.0108 | 0.9964 | 0.9964 |
|
| 86 |
+
| 0.042 | 13.9535 | 6000 | 0.0094 | 0.9967 | 0.9967 |
|
| 87 |
+
| 0.0314 | 14.4186 | 6200 | 0.0087 | 0.9969 | 0.9969 |
|
| 88 |
+
| 0.0314 | 14.8837 | 6400 | 0.0083 | 0.9971 | 0.9971 |
|
| 89 |
+
| 0.0314 | 15.3488 | 6600 | 0.0077 | 0.9973 | 0.9973 |
|
| 90 |
+
| 0.0314 | 15.8140 | 6800 | 0.0086 | 0.9972 | 0.9972 |
|
| 91 |
+
| 0.0246 | 16.2791 | 7000 | 0.0066 | 0.9979 | 0.9979 |
|
| 92 |
+
| 0.0246 | 16.7442 | 7200 | 0.0061 | 0.9977 | 0.9977 |
|
| 93 |
+
| 0.0246 | 17.2093 | 7400 | 0.0065 | 0.9979 | 0.9979 |
|
| 94 |
+
| 0.0246 | 17.6744 | 7600 | 0.0061 | 0.9980 | 0.9980 |
|
| 95 |
+
| 0.0183 | 18.1395 | 7800 | 0.0052 | 0.9981 | 0.9981 |
|
| 96 |
+
| 0.0183 | 18.6047 | 8000 | 0.0048 | 0.9983 | 0.9983 |
|
| 97 |
+
| 0.0183 | 19.0698 | 8200 | 0.0047 | 0.9983 | 0.9983 |
|
| 98 |
+
| 0.0183 | 19.5349 | 8400 | 0.0047 | 0.9983 | 0.9983 |
|
| 99 |
+
| 0.0145 | 20.0 | 8600 | 0.0047 | 0.9983 | 0.9983 |
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
### Framework versions
|
| 103 |
+
|
| 104 |
+
- Transformers 4.41.2
|
| 105 |
+
- Pytorch 2.1.2
|
| 106 |
+
- Datasets 2.19.2
|
| 107 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/xlm-roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 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": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.41.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250002
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c60b2e18dfe6969c184cc1e9a6c2b079b1fc8b387f0f03ecd8754c9a7ee35429
|
| 3 |
+
size 1112205008
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d507eba1684da293a27d6fba69c56e04123d18981a4eebf72766e1bd0b1c1820
|
| 3 |
+
size 5048
|