Initial Commit

README.md

@@ -23,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6442901234567902
+      value: 0.6512345679012346
     - name: F1
       type: f1
-      value: 0.6409333712581416
+      value: 0.6483011417314103
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,9 +36,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tweet_sentiment_multilingual dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8703
-- Accuracy: 0.6443
-- F1: 0.6409
+- Loss: 1.7268
+- Accuracy: 0.6512
+- F1: 0.6483
 
 ## Model description
 
@@ -58,8 +58,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
-- eval_batch_size: 128
+- train_batch_size: 32
+- eval_batch_size: 64
 - seed: 66
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -69,12 +69,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.787         | 2.17  | 500  | 0.8538          | 0.6508   | 0.6528 |
-| 0.4583        | 4.35  | 1000 | 1.1040          | 0.6381   | 0.6345 |
-| 0.2713        | 6.52  | 1500 | 1.3203          | 0.6439   | 0.6475 |
-| 0.1736        | 8.7   | 2000 | 1.5376          | 0.6370   | 0.6341 |
-| 0.1107        | 10.87 | 2500 | 1.8420          | 0.6512   | 0.6477 |
-| 0.0809        | 13.04 | 3000 | 1.8703          | 0.6443   | 0.6409 |
+| 0.8937        | 1.09  | 500  | 0.8922          | 0.6304   | 0.6189 |
+| 0.6912        | 2.17  | 1000 | 0.8900          | 0.6551   | 0.6516 |
+| 0.527         | 3.26  | 1500 | 0.9088          | 0.6593   | 0.6583 |
+| 0.3874        | 4.35  | 2000 | 1.1089          | 0.6516   | 0.6470 |
+| 0.2977        | 5.43  | 2500 | 1.2137          | 0.6408   | 0.6433 |
+| 0.2397        | 6.52  | 3000 | 1.2022          | 0.6431   | 0.6409 |
+| 0.203         | 7.61  | 3500 | 1.4913          | 0.6454   | 0.6469 |
+| 0.1658        | 8.7   | 4000 | 1.7268          | 0.6512   | 0.6483 |
 
 
 ### Framework versions

eval_results_cardiff.json

@@ -1 +1 @@
-{"arabic": {"f1": 0.6440711044392313, "accuracy": 0.639080459770115, "confusion_matrix": [[185, 86, 19], [48, 190, 52], [13, 96, 181]]}, "english": {"f1": 0.6885932410768928, "accuracy": 0.6873563218390805, "confusion_matrix": [[233, 49, 8], [74, 186, 30], [18, 93, 179]]}, "french": {"f1": 0.6903304872528585, "accuracy": 0.6931034482758621, "confusion_matrix": [[217, 50, 23], [28, 234, 28], [30, 108, 152]]}, "german": {"f1": 0.7236601758307936, "accuracy": 0.7229885057471265, "confusion_matrix": [[226, 46, 18], [57, 205, 28], [31, 61, 198]]}, "hindi": {"f1": 0.5123947959465417, "accuracy": 0.5114942528735632, "confusion_matrix": [[131, 118, 41], [58, 177, 55], [35, 118, 137]]}, "italian": {"f1": 0.6859667013513167, "accuracy": 0.6862068965517242, "confusion_matrix": [[174, 87, 29], [22, 246, 22], [21, 92, 177]]}, "portuguese": {"f1": 0.7410372028736448, "accuracy": 0.7379310344827587, "confusion_matrix": [[219, 62, 9], [65, 207, 18], [21, 53, 216]]}, "spanish": {"f1": 0.6715560235123673, "accuracy": 0.667816091954023, "confusion_matrix": [[210, 68, 12], [72, 185, 33], [16, 88, 186]]}, "all": {"f1": 0.670940176822901, "accuracy": 0.6682471264367816, "confusion_matrix": [[1595, 566, 159], [424, 1630, 266], [185, 709, 1426]]}}
+{"arabic": {"f1": 0.6442740029040547, "accuracy": 0.6402298850574712, "confusion_matrix": [[178, 86, 26], [45, 183, 62], [10, 84, 196]]}, "english": {"f1": 0.7057678593082327, "accuracy": 0.7068965517241379, "confusion_matrix": [[232, 48, 10], [85, 166, 39], [15, 58, 217]]}, "french": {"f1": 0.7057233249171375, "accuracy": 0.7057471264367816, "confusion_matrix": [[217, 47, 26], [32, 217, 41], [32, 78, 180]]}, "german": {"f1": 0.740952127201128, "accuracy": 0.7413793103448276, "confusion_matrix": [[221, 40, 29], [53, 198, 39], [24, 40, 226]]}, "hindi": {"f1": 0.48776920064887846, "accuracy": 0.5045977011494253, "confusion_matrix": [[231, 37, 22], [154, 92, 44], [133, 41, 116]]}, "italian": {"f1": 0.6882304946766388, "accuracy": 0.6873563218390805, "confusion_matrix": [[177, 73, 40], [24, 206, 60], [17, 58, 215]]}, "portuguese": {"f1": 0.7074958241100616, "accuracy": 0.7080459770114943, "confusion_matrix": [[199, 62, 29], [50, 186, 54], [15, 44, 231]]}, "spanish": {"f1": 0.6769025958446248, "accuracy": 0.6770114942528735, "confusion_matrix": [[196, 67, 27], [57, 172, 61], [14, 55, 221]]}, "all": {"f1": 0.6715940327292139, "accuracy": 0.6714080459770115, "confusion_matrix": [[1651, 460, 209], [500, 1420, 400], [260, 458, 1602]]}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7c2d99a78901c561eba353e20ad384b35a4e29060ee40268f2e7e5d3eee0239
+oid sha256:f7bdf78b7eefcedd000ecab83910048819c362f4f73c044167bdecfd6d034872
 size 1115316658

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2725cb43936db49b7102f3c7031365353427f45ec93c80126cbf2f8ce6f1d19e
+oid sha256:0996a93393eb044aff203732e1aa3ee82242e1d9e5c91a3b2268d5895adf4ce7
 size 4600