Model save
Browse files- README.md +85 -0
- adapter-sentiment/adapter_config.json +42 -0
- adapter-sentiment/pytorch_adapter.bin +3 -0
- default/head_config.json +19 -0
- default/pytorch_model_head.bin +3 -0
- runs/Jun09_12-34-47_a358b85c7679/events.out.tfevents.1717936494.a358b85c7679.14572.0 +2 -2
- sentiment/head_config.json +21 -0
- sentiment/pytorch_model_head.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: indolem/indobert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- f1
|
| 11 |
+
model-index:
|
| 12 |
+
- name: sentiment-seq_bn-2
|
| 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 |
+
# sentiment-seq_bn-2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.3205
|
| 24 |
+
- Accuracy: 0.8772
|
| 25 |
+
- Precision: 0.8609
|
| 26 |
+
- Recall: 0.8356
|
| 27 |
+
- F1: 0.8467
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 30
|
| 48 |
+
- eval_batch_size: 8
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 20.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 58 |
+
| 0.5517 | 1.0 | 122 | 0.5131 | 0.7168 | 0.6513 | 0.6371 | 0.6424 |
|
| 59 |
+
| 0.4833 | 2.0 | 244 | 0.4657 | 0.7519 | 0.7088 | 0.7295 | 0.7159 |
|
| 60 |
+
| 0.4318 | 3.0 | 366 | 0.4056 | 0.8120 | 0.7729 | 0.7845 | 0.7781 |
|
| 61 |
+
| 0.3905 | 4.0 | 488 | 0.3811 | 0.8421 | 0.8092 | 0.8108 | 0.8100 |
|
| 62 |
+
| 0.3626 | 5.0 | 610 | 0.3652 | 0.8496 | 0.8186 | 0.8186 | 0.8186 |
|
| 63 |
+
| 0.3331 | 6.0 | 732 | 0.3646 | 0.8546 | 0.8214 | 0.8497 | 0.8325 |
|
| 64 |
+
| 0.3134 | 7.0 | 854 | 0.3440 | 0.8672 | 0.8412 | 0.8360 | 0.8385 |
|
| 65 |
+
| 0.2927 | 8.0 | 976 | 0.3412 | 0.8647 | 0.8359 | 0.8392 | 0.8376 |
|
| 66 |
+
| 0.2833 | 9.0 | 1098 | 0.3353 | 0.8647 | 0.8352 | 0.8417 | 0.8383 |
|
| 67 |
+
| 0.2672 | 10.0 | 1220 | 0.3296 | 0.8672 | 0.8367 | 0.8510 | 0.8432 |
|
| 68 |
+
| 0.2641 | 11.0 | 1342 | 0.3270 | 0.8772 | 0.8576 | 0.8406 | 0.8484 |
|
| 69 |
+
| 0.2549 | 12.0 | 1464 | 0.3352 | 0.8697 | 0.8558 | 0.8203 | 0.8350 |
|
| 70 |
+
| 0.2534 | 13.0 | 1586 | 0.3402 | 0.8697 | 0.8602 | 0.8153 | 0.8330 |
|
| 71 |
+
| 0.2389 | 14.0 | 1708 | 0.3208 | 0.8822 | 0.8574 | 0.8592 | 0.8583 |
|
| 72 |
+
| 0.2203 | 15.0 | 1830 | 0.3279 | 0.8747 | 0.8605 | 0.8288 | 0.8422 |
|
| 73 |
+
| 0.2298 | 16.0 | 1952 | 0.3175 | 0.8747 | 0.8552 | 0.8363 | 0.8448 |
|
| 74 |
+
| 0.2227 | 17.0 | 2074 | 0.3218 | 0.8747 | 0.8586 | 0.8313 | 0.8431 |
|
| 75 |
+
| 0.2225 | 18.0 | 2196 | 0.3178 | 0.8772 | 0.8524 | 0.8506 | 0.8515 |
|
| 76 |
+
| 0.2192 | 19.0 | 2318 | 0.3199 | 0.8772 | 0.8609 | 0.8356 | 0.8467 |
|
| 77 |
+
| 0.2229 | 20.0 | 2440 | 0.3205 | 0.8772 | 0.8609 | 0.8356 | 0.8467 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.39.3
|
| 83 |
+
- Pytorch 2.3.0+cu121
|
| 84 |
+
- Datasets 2.19.1
|
| 85 |
+
- Tokenizers 0.15.2
|
adapter-sentiment/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"adapter_residual_before_ln": false,
|
| 4 |
+
"cross_adapter": false,
|
| 5 |
+
"dropout": 0.0,
|
| 6 |
+
"factorized_phm_W": true,
|
| 7 |
+
"factorized_phm_rule": false,
|
| 8 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
| 9 |
+
"init_weights": "bert",
|
| 10 |
+
"inv_adapter": null,
|
| 11 |
+
"inv_adapter_reduction_factor": null,
|
| 12 |
+
"is_parallel": false,
|
| 13 |
+
"learn_phm": true,
|
| 14 |
+
"leave_out": [],
|
| 15 |
+
"ln_after": false,
|
| 16 |
+
"ln_before": false,
|
| 17 |
+
"mh_adapter": false,
|
| 18 |
+
"non_linearity": "relu",
|
| 19 |
+
"original_ln_after": true,
|
| 20 |
+
"original_ln_before": true,
|
| 21 |
+
"output_adapter": true,
|
| 22 |
+
"phm_bias": true,
|
| 23 |
+
"phm_c_init": "normal",
|
| 24 |
+
"phm_dim": 4,
|
| 25 |
+
"phm_init_range": 0.0001,
|
| 26 |
+
"phm_layer": false,
|
| 27 |
+
"phm_rank": 1,
|
| 28 |
+
"reduction_factor": 16,
|
| 29 |
+
"residual_before_ln": true,
|
| 30 |
+
"scaling": 1.0,
|
| 31 |
+
"shared_W_phm": false,
|
| 32 |
+
"shared_phm_rule": true,
|
| 33 |
+
"use_gating": false
|
| 34 |
+
},
|
| 35 |
+
"config_id": "9076f36a74755ac4",
|
| 36 |
+
"hidden_size": 768,
|
| 37 |
+
"model_class": "BertAdapterModel",
|
| 38 |
+
"model_name": "indolem/indobert-base-uncased",
|
| 39 |
+
"model_type": "bert",
|
| 40 |
+
"name": "adapter-sentiment",
|
| 41 |
+
"version": "0.2.0"
|
| 42 |
+
}
|
adapter-sentiment/pytorch_adapter.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75c70355067111301c7f64a38e50e910cdd65da23f71ad7a5a96f112fb2fe1a5
|
| 3 |
+
size 3596006
|
default/head_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"bias": true,
|
| 5 |
+
"embedding_size": 768,
|
| 6 |
+
"head_type": "masked_lm",
|
| 7 |
+
"label2id": null,
|
| 8 |
+
"layer_norm": true,
|
| 9 |
+
"layers": 2,
|
| 10 |
+
"shift_labels": false,
|
| 11 |
+
"vocab_size": 31923
|
| 12 |
+
},
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"model_class": "BertAdapterModel",
|
| 15 |
+
"model_name": "indolem/indobert-base-uncased",
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"name": "default",
|
| 18 |
+
"version": "0.2.0"
|
| 19 |
+
}
|
default/pytorch_model_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a181f0177f3154142b57d9cab72a7e6f72dea1fe172d1a480ff543e0c17b0f3f
|
| 3 |
+
size 100566390
|
runs/Jun09_12-34-47_a358b85c7679/events.out.tfevents.1717936494.a358b85c7679.14572.0
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 sha256:45f308c84b8385ffb3995830069716e4c775febf1acb845b94c494a46cda7058
|
| 3 |
+
size 19303
|
sentiment/head_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"activation_function": "tanh",
|
| 4 |
+
"bias": true,
|
| 5 |
+
"dropout_prob": null,
|
| 6 |
+
"head_type": "classification",
|
| 7 |
+
"label2id": {
|
| 8 |
+
"0": 0,
|
| 9 |
+
"1": 1
|
| 10 |
+
},
|
| 11 |
+
"layers": 2,
|
| 12 |
+
"num_labels": 2,
|
| 13 |
+
"use_pooler": false
|
| 14 |
+
},
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"model_class": "BertAdapterModel",
|
| 17 |
+
"model_name": "indolem/indobert-base-uncased",
|
| 18 |
+
"model_type": "bert",
|
| 19 |
+
"name": "sentiment",
|
| 20 |
+
"version": "0.2.0"
|
| 21 |
+
}
|
sentiment/pytorch_model_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bb5a2fbe8433eb2e87a961b2cbae02e85bb45e220d21ed99729a68260484561
|
| 3 |
+
size 2370664
|