Model save
Browse files- .gitattributes +1 -0
- README.md +69 -69
- all_results.json +7 -7
- final/config.json +14 -18
- final/model.safetensors +2 -2
- final/special_tokens_map.json +20 -6
- final/tokenizer.json +0 -0
- final/tokenizer_config.json +20 -29
- final/training_args.bin +2 -2
- model.safetensors +1 -1
- test_results.json +7 -7
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
license:
|
| 4 |
-
base_model:
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
|
@@ -9,22 +9,22 @@ metrics:
|
|
| 9 |
- recall
|
| 10 |
- accuracy
|
| 11 |
model-index:
|
| 12 |
-
- name:
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
-
#
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 1.
|
| 24 |
-
- Precision: 0.
|
| 25 |
- Recall: 0.3533
|
| 26 |
-
- F1 Macro: 0.
|
| 27 |
-
- Accuracy: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -56,66 +56,66 @@ The following hyperparameters were used during training:
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|
|
| 59 |
-
| No log | 0 | 0 |
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
|
| 120 |
|
| 121 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: intfloat/multilingual-e5-large-instruct
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
|
|
|
| 9 |
- recall
|
| 10 |
- accuracy
|
| 11 |
model-index:
|
| 12 |
+
- name: multilingual-e5-large-instruct-edu-scorer-lr5e5-bs32
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
+
# multilingual-e5-large-instruct-edu-scorer-lr5e5-bs32
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0423
|
| 24 |
+
- Precision: 0.4783
|
| 25 |
- Recall: 0.3533
|
| 26 |
+
- F1 Macro: 0.3508
|
| 27 |
+
- Accuracy: 0.38
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|
|
| 59 |
+
| No log | 0 | 0 | 4.0694 | 0.0587 | 0.1667 | 0.0869 | 0.3524 |
|
| 60 |
+
| 0.834 | 0.3368 | 1000 | 0.7770 | 0.4163 | 0.3268 | 0.3177 | 0.4876 |
|
| 61 |
+
| 0.8535 | 0.6736 | 2000 | 0.9632 | 0.3999 | 0.3404 | 0.3236 | 0.3578 |
|
| 62 |
+
| 0.7996 | 1.0104 | 3000 | 0.8151 | 0.4568 | 0.3298 | 0.3278 | 0.5098 |
|
| 63 |
+
| 0.8055 | 1.3473 | 4000 | 0.8134 | 0.4109 | 0.3380 | 0.3268 | 0.3946 |
|
| 64 |
+
| 0.7807 | 1.6841 | 5000 | 0.7303 | 0.4170 | 0.3698 | 0.3717 | 0.4824 |
|
| 65 |
+
| 0.7628 | 2.0209 | 6000 | 0.8066 | 0.4310 | 0.3406 | 0.3296 | 0.3928 |
|
| 66 |
+
| 0.7737 | 2.3577 | 7000 | 0.7125 | 0.4856 | 0.3456 | 0.3491 | 0.5032 |
|
| 67 |
+
| 0.7246 | 2.6945 | 8000 | 0.7268 | 0.5744 | 0.3593 | 0.3612 | 0.4676 |
|
| 68 |
+
| 0.7179 | 3.0313 | 9000 | 0.7028 | 0.4875 | 0.3668 | 0.3726 | 0.4916 |
|
| 69 |
+
| 0.715 | 3.3681 | 10000 | 0.6926 | 0.4094 | 0.3570 | 0.3583 | 0.5116 |
|
| 70 |
+
| 0.696 | 3.7050 | 11000 | 0.7401 | 0.4944 | 0.3689 | 0.3685 | 0.459 |
|
| 71 |
+
| 0.7221 | 4.0418 | 12000 | 0.6773 | 0.5800 | 0.3632 | 0.3707 | 0.5256 |
|
| 72 |
+
| 0.7425 | 4.3786 | 13000 | 0.7350 | 0.4280 | 0.3918 | 0.3939 | 0.489 |
|
| 73 |
+
| 0.7426 | 4.7154 | 14000 | 0.7564 | 0.4749 | 0.3715 | 0.3711 | 0.4656 |
|
| 74 |
+
| 0.6576 | 5.0522 | 15000 | 0.6928 | 0.4105 | 0.3515 | 0.3527 | 0.5278 |
|
| 75 |
+
| 0.7033 | 5.3890 | 16000 | 0.6894 | 0.4532 | 0.3863 | 0.3908 | 0.5138 |
|
| 76 |
+
| 0.6813 | 5.7258 | 17000 | 0.6655 | 0.4101 | 0.3506 | 0.3380 | 0.5216 |
|
| 77 |
+
| 0.6653 | 6.0626 | 18000 | 0.6813 | 0.4161 | 0.3429 | 0.3404 | 0.5248 |
|
| 78 |
+
| 0.7086 | 6.3995 | 19000 | 0.6744 | 0.5219 | 0.3909 | 0.4010 | 0.5076 |
|
| 79 |
+
| 0.6658 | 6.7363 | 20000 | 0.6524 | 0.5000 | 0.3788 | 0.3852 | 0.5226 |
|
| 80 |
+
| 0.6843 | 7.0731 | 21000 | 0.6561 | 0.4176 | 0.3527 | 0.3502 | 0.5256 |
|
| 81 |
+
| 0.6927 | 7.4099 | 22000 | 0.6783 | 0.4554 | 0.3810 | 0.3843 | 0.5006 |
|
| 82 |
+
| 0.6708 | 7.7467 | 23000 | 0.7420 | 0.3982 | 0.3270 | 0.3197 | 0.516 |
|
| 83 |
+
| 0.646 | 8.0835 | 24000 | 0.6684 | 0.4776 | 0.3820 | 0.3890 | 0.491 |
|
| 84 |
+
| 0.6577 | 8.4203 | 25000 | 0.6562 | 0.4946 | 0.3718 | 0.3783 | 0.5358 |
|
| 85 |
+
| 0.68 | 8.7572 | 26000 | 0.6628 | 0.4841 | 0.3940 | 0.4032 | 0.5168 |
|
| 86 |
+
| 0.6827 | 9.0940 | 27000 | 0.6508 | 0.4947 | 0.3715 | 0.3753 | 0.5104 |
|
| 87 |
+
| 0.6611 | 9.4308 | 28000 | 0.6434 | 0.5237 | 0.3862 | 0.3981 | 0.5378 |
|
| 88 |
+
| 0.6147 | 9.7676 | 29000 | 0.6597 | 0.4199 | 0.3584 | 0.3590 | 0.5376 |
|
| 89 |
+
| 0.638 | 10.1044 | 30000 | 0.6330 | 0.5038 | 0.3851 | 0.3902 | 0.5342 |
|
| 90 |
+
| 0.6286 | 10.4412 | 31000 | 0.6579 | 0.4508 | 0.3865 | 0.3926 | 0.5 |
|
| 91 |
+
| 0.6352 | 10.7780 | 32000 | 0.6586 | 0.4467 | 0.3917 | 0.3982 | 0.5096 |
|
| 92 |
+
| 0.6369 | 11.1149 | 33000 | 0.6365 | 0.4970 | 0.3846 | 0.3911 | 0.5248 |
|
| 93 |
+
| 0.624 | 11.4517 | 34000 | 0.7212 | 0.4463 | 0.3806 | 0.3796 | 0.457 |
|
| 94 |
+
| 0.6502 | 11.7885 | 35000 | 0.6419 | 0.4002 | 0.3771 | 0.3743 | 0.5274 |
|
| 95 |
+
| 0.6133 | 12.1253 | 36000 | 0.6765 | 0.3968 | 0.3506 | 0.3457 | 0.535 |
|
| 96 |
+
| 0.604 | 12.4621 | 37000 | 0.6361 | 0.4637 | 0.3833 | 0.3908 | 0.5334 |
|
| 97 |
+
| 0.6426 | 12.7989 | 38000 | 0.6376 | 0.4137 | 0.3631 | 0.3639 | 0.5352 |
|
| 98 |
+
| 0.6227 | 13.1357 | 39000 | 0.6637 | 0.4176 | 0.3579 | 0.3554 | 0.5406 |
|
| 99 |
+
| 0.6275 | 13.4725 | 40000 | 0.6446 | 0.4482 | 0.3989 | 0.4050 | 0.528 |
|
| 100 |
+
| 0.6545 | 13.8094 | 41000 | 0.6526 | 0.3960 | 0.3524 | 0.3479 | 0.534 |
|
| 101 |
+
| 0.5786 | 14.1462 | 42000 | 0.6280 | 0.4445 | 0.3847 | 0.3907 | 0.5358 |
|
| 102 |
+
| 0.6123 | 14.4830 | 43000 | 0.6351 | 0.4075 | 0.3799 | 0.3805 | 0.5234 |
|
| 103 |
+
| 0.5885 | 14.8198 | 44000 | 0.6633 | 0.4102 | 0.3775 | 0.3743 | 0.4986 |
|
| 104 |
+
| 0.6052 | 15.1566 | 45000 | 0.6437 | 0.4354 | 0.3940 | 0.3968 | 0.5226 |
|
| 105 |
+
| 0.6066 | 15.4934 | 46000 | 0.6305 | 0.4056 | 0.3724 | 0.3732 | 0.5382 |
|
| 106 |
+
| 0.6106 | 15.8302 | 47000 | 0.6317 | 0.4078 | 0.3802 | 0.3818 | 0.5298 |
|
| 107 |
+
| 0.5995 | 16.1671 | 48000 | 0.6644 | 0.4267 | 0.3933 | 0.3947 | 0.5078 |
|
| 108 |
+
| 0.6001 | 16.5039 | 49000 | 0.6294 | 0.4152 | 0.3830 | 0.3839 | 0.5424 |
|
| 109 |
+
| 0.5553 | 16.8407 | 50000 | 0.6293 | 0.4150 | 0.3829 | 0.3838 | 0.5448 |
|
| 110 |
+
| 0.5787 | 17.1775 | 51000 | 0.6284 | 0.4143 | 0.3813 | 0.3829 | 0.5404 |
|
| 111 |
+
| 0.5724 | 17.5143 | 52000 | 0.6255 | 0.4178 | 0.3810 | 0.3819 | 0.544 |
|
| 112 |
+
| 0.5558 | 17.8511 | 53000 | 0.6251 | 0.4187 | 0.3827 | 0.3840 | 0.539 |
|
| 113 |
+
| 0.533 | 18.1879 | 54000 | 0.6263 | 0.4175 | 0.3816 | 0.3824 | 0.538 |
|
| 114 |
+
| 0.5612 | 18.5248 | 55000 | 0.6302 | 0.4122 | 0.3870 | 0.3880 | 0.5382 |
|
| 115 |
+
| 0.5594 | 18.8616 | 56000 | 0.6230 | 0.4203 | 0.3800 | 0.3807 | 0.5402 |
|
| 116 |
+
| 0.565 | 19.1984 | 57000 | 0.6264 | 0.4117 | 0.3789 | 0.3799 | 0.5346 |
|
| 117 |
+
| 0.5533 | 19.5352 | 58000 | 0.6261 | 0.4153 | 0.3825 | 0.3837 | 0.537 |
|
| 118 |
+
| 0.5459 | 19.8720 | 59000 | 0.6289 | 0.4128 | 0.3846 | 0.3853 | 0.5342 |
|
| 119 |
|
| 120 |
|
| 121 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_macro": 0.
|
| 5 |
-
"eval_loss": 1.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
"eval_recall": 0.35333333333333333,
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.38,
|
| 4 |
+
"eval_f1_macro": 0.350831072607419,
|
| 5 |
+
"eval_loss": 1.0422507524490356,
|
| 6 |
+
"eval_precision": 0.47828045975228123,
|
| 7 |
"eval_recall": 0.35333333333333333,
|
| 8 |
+
"eval_runtime": 5.9925,
|
| 9 |
+
"eval_samples_per_second": 91.782,
|
| 10 |
+
"eval_steps_per_second": 3.004
|
| 11 |
}
|
final/config.json
CHANGED
|
@@ -1,38 +1,34 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
-
"
|
| 8 |
-
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.0,
|
| 11 |
-
"hidden_size":
|
| 12 |
"id2label": {
|
| 13 |
"0": "LABEL_0"
|
| 14 |
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size":
|
| 17 |
"label2id": {
|
| 18 |
"LABEL_0": 0
|
| 19 |
},
|
| 20 |
-
"layer_norm_eps": 1e-
|
| 21 |
-
"max_position_embeddings":
|
| 22 |
-
"model_type": "
|
| 23 |
-
"num_attention_heads":
|
| 24 |
-
"num_hidden_layers":
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"pooler_num_attention_heads": 12,
|
| 28 |
-
"pooler_num_fc_layers": 3,
|
| 29 |
-
"pooler_size_per_head": 128,
|
| 30 |
-
"pooler_type": "first_token_transform",
|
| 31 |
"position_embedding_type": "absolute",
|
| 32 |
"problem_type": "regression",
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.53.2",
|
| 35 |
-
"type_vocab_size":
|
| 36 |
"use_cache": true,
|
| 37 |
-
"vocab_size":
|
| 38 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"XLMRobertaForSequenceClassification"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
"classifier_dropout": 0.0,
|
| 8 |
+
"eos_token_id": 2,
|
|
|
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
"id2label": {
|
| 13 |
"0": "LABEL_0"
|
| 14 |
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 4096,
|
| 17 |
"label2id": {
|
| 18 |
"LABEL_0": 0
|
| 19 |
},
|
| 20 |
+
"layer_norm_eps": 1e-05,
|
| 21 |
+
"max_position_embeddings": 514,
|
| 22 |
+
"model_type": "xlm-roberta",
|
| 23 |
+
"num_attention_heads": 16,
|
| 24 |
+
"num_hidden_layers": 24,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"position_embedding_type": "absolute",
|
| 28 |
"problem_type": "regression",
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
"transformers_version": "4.53.2",
|
| 31 |
+
"type_vocab_size": 1,
|
| 32 |
"use_cache": true,
|
| 33 |
+
"vocab_size": 250002
|
| 34 |
}
|
final/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44560c8557c5ab25d27853380ba4d4f214e9c3b2ace5adba61e78be1b64a6720
|
| 3 |
+
size 2239614572
|
final/special_tokens_map.json
CHANGED
|
@@ -1,34 +1,48 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": {
|
| 3 |
-
"content": "
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
-
"
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"sep_token": {
|
| 24 |
-
"content": "
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"unk_token": {
|
| 31 |
-
"content": "
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
| 44 |
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
"lstrip": false,
|
| 47 |
"normalized": false,
|
| 48 |
"rstrip": false,
|
final/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
final/tokenizer_config.json
CHANGED
|
@@ -1,65 +1,56 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
-
"content": "
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
-
"content": "
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
-
"content": "
|
| 37 |
-
"lstrip":
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
|
|
|
| 48 |
"extra_special_tokens": {},
|
| 49 |
-
"mask_token": "
|
| 50 |
-
"max_length": 75,
|
| 51 |
"model_max_length": 512,
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"padding_side": "right",
|
| 57 |
-
"sep_token": "[SEP]",
|
| 58 |
-
"stride": 0,
|
| 59 |
-
"strip_accents": null,
|
| 60 |
-
"tokenize_chinese_chars": true,
|
| 61 |
-
"tokenizer_class": "BertTokenizer",
|
| 62 |
-
"truncation_side": "right",
|
| 63 |
-
"truncation_strategy": "longest_first",
|
| 64 |
-
"unk_token": "[UNK]"
|
| 65 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"additional_special_tokens": [],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "<mask>",
|
|
|
|
| 51 |
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
}
|
final/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d4dd3ba0eab0d02bdc1ce7d0cb491b8dadf1115b80f175cba58ce9d587d27c7
|
| 3 |
+
size 5905
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2239614572
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44560c8557c5ab25d27853380ba4d4f214e9c3b2ace5adba61e78be1b64a6720
|
| 3 |
size 2239614572
|
test_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_macro": 0.
|
| 5 |
-
"eval_loss": 1.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
"eval_recall": 0.35333333333333333,
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.38,
|
| 4 |
+
"eval_f1_macro": 0.350831072607419,
|
| 5 |
+
"eval_loss": 1.0422507524490356,
|
| 6 |
+
"eval_precision": 0.47828045975228123,
|
| 7 |
"eval_recall": 0.35333333333333333,
|
| 8 |
+
"eval_runtime": 5.9925,
|
| 9 |
+
"eval_samples_per_second": 91.782,
|
| 10 |
+
"eval_steps_per_second": 3.004
|
| 11 |
}
|