Initial Commit
Browse files- README.md +51 -51
- config.json +1 -1
- eval_results_cardiff.json +1 -0
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# scenario-KD-PR-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all55
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss:
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- F1: 0.
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -53,52 +53,52 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 55 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 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 |
|
| 103 |
|
| 104 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model: haryoaw/scenario-MDBT-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
|
|
| 18 |
|
| 19 |
# scenario-KD-PR-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all55
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all) on the tweet_sentiment_multilingual dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.2180
|
| 24 |
+
- Accuracy: 0.5999
|
| 25 |
+
- F1: 0.6008
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 55 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
| 56 |
+
| 1.2423 | 1.09 | 500 | 1.2214 | 0.4842 | 0.4591 |
|
| 57 |
+
| 1.1465 | 2.17 | 1000 | 1.2081 | 0.5498 | 0.5406 |
|
| 58 |
+
| 1.089 | 3.26 | 1500 | 1.2345 | 0.5540 | 0.5476 |
|
| 59 |
+
| 1.043 | 4.35 | 2000 | 1.2340 | 0.5756 | 0.5777 |
|
| 60 |
+
| 1.01 | 5.43 | 2500 | 1.2397 | 0.5706 | 0.5717 |
|
| 61 |
+
| 0.9787 | 6.52 | 3000 | 1.2536 | 0.5718 | 0.5723 |
|
| 62 |
+
| 0.9656 | 7.61 | 3500 | 1.2564 | 0.5579 | 0.5603 |
|
| 63 |
+
| 0.9505 | 8.7 | 4000 | 1.2641 | 0.5644 | 0.5660 |
|
| 64 |
+
| 0.9432 | 9.78 | 4500 | 1.2385 | 0.5880 | 0.5876 |
|
| 65 |
+
| 0.9304 | 10.87 | 5000 | 1.2612 | 0.5864 | 0.5862 |
|
| 66 |
+
| 0.9245 | 11.96 | 5500 | 1.2567 | 0.5748 | 0.5728 |
|
| 67 |
+
| 0.9189 | 13.04 | 6000 | 1.2463 | 0.5745 | 0.5745 |
|
| 68 |
+
| 0.9131 | 14.13 | 6500 | 1.2599 | 0.5729 | 0.5738 |
|
| 69 |
+
| 0.9098 | 15.22 | 7000 | 1.2614 | 0.5706 | 0.5704 |
|
| 70 |
+
| 0.9052 | 16.3 | 7500 | 1.2468 | 0.5741 | 0.5748 |
|
| 71 |
+
| 0.9013 | 17.39 | 8000 | 1.2550 | 0.5756 | 0.5775 |
|
| 72 |
+
| 0.8972 | 18.48 | 8500 | 1.2661 | 0.5733 | 0.5743 |
|
| 73 |
+
| 0.8972 | 19.57 | 9000 | 1.2506 | 0.5783 | 0.5780 |
|
| 74 |
+
| 0.8912 | 20.65 | 9500 | 1.2519 | 0.5737 | 0.5752 |
|
| 75 |
+
| 0.8903 | 21.74 | 10000 | 1.2313 | 0.5795 | 0.5782 |
|
| 76 |
+
| 0.8868 | 22.83 | 10500 | 1.2384 | 0.5895 | 0.5896 |
|
| 77 |
+
| 0.8847 | 23.91 | 11000 | 1.2474 | 0.5752 | 0.5736 |
|
| 78 |
+
| 0.8834 | 25.0 | 11500 | 1.2458 | 0.5791 | 0.5795 |
|
| 79 |
+
| 0.8815 | 26.09 | 12000 | 1.2548 | 0.5748 | 0.5739 |
|
| 80 |
+
| 0.8794 | 27.17 | 12500 | 1.2378 | 0.5864 | 0.5857 |
|
| 81 |
+
| 0.8791 | 28.26 | 13000 | 1.2327 | 0.5968 | 0.5953 |
|
| 82 |
+
| 0.8749 | 29.35 | 13500 | 1.2249 | 0.5949 | 0.5935 |
|
| 83 |
+
| 0.8748 | 30.43 | 14000 | 1.2309 | 0.5938 | 0.5905 |
|
| 84 |
+
| 0.8734 | 31.52 | 14500 | 1.2242 | 0.5880 | 0.5885 |
|
| 85 |
+
| 0.872 | 32.61 | 15000 | 1.2372 | 0.5841 | 0.5856 |
|
| 86 |
+
| 0.8712 | 33.7 | 15500 | 1.2394 | 0.5783 | 0.5800 |
|
| 87 |
+
| 0.87 | 34.78 | 16000 | 1.2363 | 0.5922 | 0.5921 |
|
| 88 |
+
| 0.8692 | 35.87 | 16500 | 1.2375 | 0.5903 | 0.5916 |
|
| 89 |
+
| 0.8677 | 36.96 | 17000 | 1.2341 | 0.5968 | 0.5951 |
|
| 90 |
+
| 0.8672 | 38.04 | 17500 | 1.2227 | 0.6038 | 0.6013 |
|
| 91 |
+
| 0.8657 | 39.13 | 18000 | 1.2250 | 0.5899 | 0.5904 |
|
| 92 |
+
| 0.865 | 40.22 | 18500 | 1.2275 | 0.5949 | 0.5952 |
|
| 93 |
+
| 0.865 | 41.3 | 19000 | 1.2196 | 0.5953 | 0.5958 |
|
| 94 |
+
| 0.864 | 42.39 | 19500 | 1.2375 | 0.5818 | 0.5815 |
|
| 95 |
+
| 0.8636 | 43.48 | 20000 | 1.2373 | 0.5849 | 0.5856 |
|
| 96 |
+
| 0.8635 | 44.57 | 20500 | 1.2292 | 0.5930 | 0.5940 |
|
| 97 |
+
| 0.8622 | 45.65 | 21000 | 1.2243 | 0.5903 | 0.5914 |
|
| 98 |
+
| 0.8619 | 46.74 | 21500 | 1.2198 | 0.5984 | 0.5992 |
|
| 99 |
+
| 0.8608 | 47.83 | 22000 | 1.2175 | 0.6046 | 0.6054 |
|
| 100 |
+
| 0.8621 | 48.91 | 22500 | 1.2179 | 0.5995 | 0.6004 |
|
| 101 |
+
| 0.8606 | 50.0 | 23000 | 1.2180 | 0.5999 | 0.6008 |
|
| 102 |
|
| 103 |
|
| 104 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"DebertaForSequenceClassificationKD"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "haryoaw/scenario-MDBT-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all",
|
| 3 |
"architectures": [
|
| 4 |
"DebertaForSequenceClassificationKD"
|
| 5 |
],
|
eval_results_cardiff.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"arabic": {"f1": 0.5612630228065163, "accuracy": 0.5586206896551724, "confusion_matrix": [[155, 101, 34], [57, 177, 56], [33, 103, 154]]}, "english": {"f1": 0.6449384250034303, "accuracy": 0.6459770114942529, "confusion_matrix": [[225, 50, 15], [83, 171, 36], [41, 83, 166]]}, "french": {"f1": 0.6468819435660574, "accuracy": 0.6471264367816092, "confusion_matrix": [[198, 47, 45], [32, 201, 57], [43, 83, 164]]}, "german": {"f1": 0.6930782783320829, "accuracy": 0.6931034482758621, "confusion_matrix": [[201, 51, 38], [48, 214, 28], [39, 63, 188]]}, "hindi": {"f1": 0.45263678447417727, "accuracy": 0.4528735632183908, "confusion_matrix": [[140, 85, 65], [78, 129, 83], [88, 77, 125]]}, "italian": {"f1": 0.5675275816402665, "accuracy": 0.5712643678160919, "confusion_matrix": [[147, 84, 59], [20, 212, 58], [50, 102, 138]]}, "portuguese": {"f1": 0.6265368086078835, "accuracy": 0.6241379310344828, "confusion_matrix": [[187, 82, 21], [66, 173, 51], [34, 73, 183]]}, "spanish": {"f1": 0.5742844725965642, "accuracy": 0.5735632183908046, "confusion_matrix": [[179, 73, 38], [71, 153, 66], [43, 80, 167]]}, "all": {"f1": 0.5959713022267769, "accuracy": 0.5952586206896552, "confusion_matrix": [[1430, 577, 313], [481, 1409, 430], [368, 648, 1304]]}}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 946740394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9410f1db316c62c25aade5cce7321dfa98ca92f1cae2a4049b5d2ca901f1eb1f
|
| 3 |
size 946740394
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:631f5fe9fb15addad2d2a7dc0554e507cc3f01a591847e41314c5f5747b45133
|
| 3 |
size 4664
|