commit files to HF hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# `vocabtrimmer/xlm-roberta-base-trimmed-en-tweet-sentiment-en`
|
| 2 |
+
This model is a fine-tuned version of [/home/asahiushio/Projects/lm-vocab-trimmer/ckpts/xlm-roberta-base-trimmed-en](https://huggingface.co//home/asahiushio/Projects/lm-vocab-trimmer/ckpts/xlm-roberta-base-trimmed-en) on the
|
| 3 |
+
[cardiffnlp/tweet_sentiment_multilingual](https://huggingface.co/datasets/cardiffnlp/tweet_sentiment_multilingual) (english).
|
| 4 |
+
Following metrics are computed on the `test` split of
|
| 5 |
+
[cardiffnlp/tweet_sentiment_multilingual](https://huggingface.co/datasets/cardiffnlp/tweet_sentiment_multilingual)(english).
|
| 6 |
+
|
| 7 |
+
| | eval_f1_micro | eval_recall_micro | eval_precision_micro | eval_f1_macro | eval_recall_macro | eval_precision_macro | eval_accuracy |
|
| 8 |
+
|---:|----------------:|--------------------:|-----------------------:|----------------:|--------------------:|-----------------------:|----------------:|
|
| 9 |
+
| 0 | 68.28 | 68.28 | 68.28 | 67.86 | 68.28 | 68.19 | 68.28 |
|
| 10 |
+
|
| 11 |
+
Check the result file [here](https://huggingface.co/vocabtrimmer/xlm-roberta-base-trimmed-en-tweet-sentiment-en/raw/main/eval.json).
|
eval.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eval_loss": 1.0542951822280884, "eval_f1_micro": 0.6827586206896552, "eval_recall_micro": 0.6827586206896552, "eval_precision_micro": 0.6827586206896552, "eval_f1_macro": 0.6785681192417664, "eval_recall_macro": 0.6827586206896553, "eval_precision_macro": 0.6818971741143095, "eval_accuracy": 0.6827586206896552, "eval_runtime": 2.3091, "eval_samples_per_second": 376.77, "eval_steps_per_second": 47.204}
|