Initial Commit
Browse files- README.md +104 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: haryoaw/teacher_tweet_eval_sentiment_xlmr_base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- tweet_eval
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: scenario-kd-from-post-finetune-gold-silver-div-2-data-tweet_eval-sentiment-model
|
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-from-post-finetune-gold-silver-div-2-data-tweet_eval-sentiment-model
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [haryoaw/teacher_tweet_eval_sentiment_xlmr_base](https://huggingface.co/haryoaw/teacher_tweet_eval_sentiment_xlmr_base) on the tweet_eval dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.3344
|
24 |
+
- Accuracy: 0.734
|
25 |
+
- F1: 0.7061
|
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 |
+
| 1.838 | 0.7 | 1000 | 1.8178 | 0.71 | 0.6779 |
|
57 |
+
| 1.3953 | 1.4 | 2000 | 1.5675 | 0.72 | 0.6988 |
|
58 |
+
| 1.2818 | 2.1 | 3000 | 1.6086 | 0.7205 | 0.6892 |
|
59 |
+
| 1.1321 | 2.81 | 4000 | 1.6146 | 0.7235 | 0.7013 |
|
60 |
+
| 0.9348 | 3.51 | 5000 | 1.6493 | 0.719 | 0.6902 |
|
61 |
+
| 0.9139 | 4.21 | 6000 | 1.5044 | 0.719 | 0.7026 |
|
62 |
+
| 0.8836 | 4.91 | 7000 | 1.4467 | 0.728 | 0.7068 |
|
63 |
+
| 0.7857 | 5.61 | 8000 | 1.4894 | 0.727 | 0.6971 |
|
64 |
+
| 0.7366 | 6.31 | 9000 | 1.4895 | 0.7265 | 0.7052 |
|
65 |
+
| 0.7471 | 7.01 | 10000 | 1.4055 | 0.73 | 0.7089 |
|
66 |
+
| 0.7067 | 7.71 | 11000 | 1.4671 | 0.729 | 0.7055 |
|
67 |
+
| 0.6668 | 8.42 | 12000 | 1.4966 | 0.729 | 0.7011 |
|
68 |
+
| 0.6608 | 9.12 | 13000 | 1.4326 | 0.722 | 0.7006 |
|
69 |
+
| 0.6371 | 9.82 | 14000 | 1.4281 | 0.724 | 0.7005 |
|
70 |
+
| 0.6047 | 10.52 | 15000 | 1.4260 | 0.7225 | 0.6954 |
|
71 |
+
| 0.5929 | 11.22 | 16000 | 1.4013 | 0.7235 | 0.6974 |
|
72 |
+
| 0.5963 | 11.92 | 17000 | 1.3812 | 0.727 | 0.7053 |
|
73 |
+
| 0.5777 | 12.62 | 18000 | 1.3694 | 0.727 | 0.7029 |
|
74 |
+
| 0.5587 | 13.32 | 19000 | 1.4384 | 0.724 | 0.6951 |
|
75 |
+
| 0.5631 | 14.03 | 20000 | 1.3488 | 0.732 | 0.7097 |
|
76 |
+
| 0.538 | 14.73 | 21000 | 1.3758 | 0.7285 | 0.7042 |
|
77 |
+
| 0.5365 | 15.43 | 22000 | 1.3314 | 0.7305 | 0.7059 |
|
78 |
+
| 0.5339 | 16.13 | 23000 | 1.3576 | 0.729 | 0.7046 |
|
79 |
+
| 0.5232 | 16.83 | 24000 | 1.3652 | 0.732 | 0.7065 |
|
80 |
+
| 0.5082 | 17.53 | 25000 | 1.4092 | 0.729 | 0.7015 |
|
81 |
+
| 0.5015 | 18.23 | 26000 | 1.3548 | 0.726 | 0.7019 |
|
82 |
+
| 0.5035 | 18.93 | 27000 | 1.3637 | 0.7335 | 0.7076 |
|
83 |
+
| 0.4932 | 19.64 | 28000 | 1.3489 | 0.7205 | 0.6968 |
|
84 |
+
| 0.4867 | 20.34 | 29000 | 1.3753 | 0.7385 | 0.7135 |
|
85 |
+
| 0.4819 | 21.04 | 30000 | 1.3652 | 0.727 | 0.7050 |
|
86 |
+
| 0.4782 | 21.74 | 31000 | 1.3339 | 0.743 | 0.7194 |
|
87 |
+
| 0.4712 | 22.44 | 32000 | 1.3229 | 0.728 | 0.7059 |
|
88 |
+
| 0.4677 | 23.14 | 33000 | 1.3203 | 0.7365 | 0.7114 |
|
89 |
+
| 0.4736 | 23.84 | 34000 | 1.3605 | 0.7345 | 0.7114 |
|
90 |
+
| 0.4551 | 24.54 | 35000 | 1.3491 | 0.724 | 0.7016 |
|
91 |
+
| 0.458 | 25.25 | 36000 | 1.3663 | 0.739 | 0.7063 |
|
92 |
+
| 0.4545 | 25.95 | 37000 | 1.3502 | 0.734 | 0.7087 |
|
93 |
+
| 0.4471 | 26.65 | 38000 | 1.3435 | 0.7375 | 0.7100 |
|
94 |
+
| 0.441 | 27.35 | 39000 | 1.3069 | 0.7435 | 0.7155 |
|
95 |
+
| 0.4495 | 28.05 | 40000 | 1.3175 | 0.7285 | 0.7037 |
|
96 |
+
| 0.4411 | 28.75 | 41000 | 1.3344 | 0.734 | 0.7061 |
|
97 |
+
|
98 |
+
|
99 |
+
### Framework versions
|
100 |
+
|
101 |
+
- Transformers 4.33.3
|
102 |
+
- Pytorch 2.0.1
|
103 |
+
- Datasets 2.14.5
|
104 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/teacher_tweet_eval_sentiment_xlmr_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 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "xlm-roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 6,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.33.3",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250002
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d13cb5f290a21d301b9333aa0e51bedc8caa68c6123b37adfa93100852ad260
|
3 |
+
size 942110641
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94b978530e87bd8f566adaef1740d38f54c1869935bbdc2068b6c468856c66d3
|
3 |
+
size 4219
|