haryoaw commited on
Commit
900d779
1 Parent(s): f8f3788

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +80 -0
  2. config.json +29 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: haryoaw/scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - indolem_sentiment
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: scenario-kd_weight_copy-data-indolem_sentiment-model-xlmr_base_trained
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
+ # scenario-kd_weight_copy-data-indolem_sentiment-model-xlmr_base_trained
20
+
21
+ This model is a fine-tuned version of [haryoaw/scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base](https://huggingface.co/haryoaw/scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base) on the indolem_sentiment dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 4.8332
24
+ - Accuracy: 0.8471
25
+ - F1: 0.7336
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 32
46
+ - eval_batch_size: 32
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 6969
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
56
+ | No log | 0.88 | 100 | 7.3908 | 0.7419 | 0.6601 |
57
+ | No log | 1.75 | 200 | 3.5626 | 0.8571 | 0.7816 |
58
+ | No log | 2.63 | 300 | 8.7677 | 0.7218 | 0.6706 |
59
+ | No log | 3.51 | 400 | 4.4989 | 0.8346 | 0.7402 |
60
+ | 3.8583 | 4.39 | 500 | 4.6632 | 0.8271 | 0.7273 |
61
+ | 3.8583 | 5.26 | 600 | 4.5488 | 0.8496 | 0.7619 |
62
+ | 3.8583 | 6.14 | 700 | 4.0955 | 0.8697 | 0.7759 |
63
+ | 3.8583 | 7.02 | 800 | 4.4503 | 0.8471 | 0.7404 |
64
+ | 3.8583 | 7.89 | 900 | 4.7169 | 0.8346 | 0.7556 |
65
+ | 1.2007 | 8.77 | 1000 | 3.8991 | 0.8697 | 0.7739 |
66
+ | 1.2007 | 9.65 | 1100 | 5.7272 | 0.8321 | 0.6794 |
67
+ | 1.2007 | 10.53 | 1200 | 4.7281 | 0.8596 | 0.7647 |
68
+ | 1.2007 | 11.4 | 1300 | 8.4804 | 0.8095 | 0.5682 |
69
+ | 1.2007 | 12.28 | 1400 | 4.2305 | 0.8546 | 0.7411 |
70
+ | 0.7006 | 13.16 | 1500 | 4.7921 | 0.8371 | 0.7137 |
71
+ | 0.7006 | 14.04 | 1600 | 4.6111 | 0.8471 | 0.7215 |
72
+ | 0.7006 | 14.91 | 1700 | 4.8332 | 0.8471 | 0.7336 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.33.3
78
+ - Pytorch 2.0.1
79
+ - Datasets 2.14.5
80
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "haryoaw/scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassificationKD"
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": 6,
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": "4.33.3",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b4e185059ee5a396e623d58d240297a99e144bacd52ee474e48a3bebe8eccc
3
+ size 942107569
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af86953ae3f891c1e656c9206355bf37b9581213011bcab293acecb7fd5606a
3
+ size 4219