Initial Commit

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: mit
 base_model: microsoft/mdeberta-v3-base
 tags:
@@ -18,9 +19,9 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.7960
-- Accuracy: 0.3448
-- F1: 0.3121
+- Loss: 5.0909
+- Accuracy: 0.3682
+- F1: 0.3646
 
 ## Model description
 
@@ -49,30 +50,30 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.72  | 100  | 1.1461          | 0.3593   | 0.3245 |
-| No log        | 3.45  | 200  | 1.9614          | 0.3611   | 0.3512 |
-| No log        | 5.17  | 300  | 2.6180          | 0.3492   | 0.3157 |
-| No log        | 6.9   | 400  | 3.1787          | 0.3673   | 0.3633 |
-| 0.4792        | 8.62  | 500  | 3.7077          | 0.3527   | 0.3312 |
-| 0.4792        | 10.34 | 600  | 4.5969          | 0.3549   | 0.3296 |
-| 0.4792        | 12.07 | 700  | 4.8433          | 0.3483   | 0.3159 |
-| 0.4792        | 13.79 | 800  | 5.1229          | 0.3602   | 0.3462 |
-| 0.4792        | 15.52 | 900  | 5.3356          | 0.3554   | 0.3354 |
-| 0.0195        | 17.24 | 1000 | 5.5333          | 0.3567   | 0.3421 |
-| 0.0195        | 18.97 | 1100 | 5.4819          | 0.3660   | 0.3534 |
-| 0.0195        | 20.69 | 1200 | 5.6908          | 0.3607   | 0.3366 |
-| 0.0195        | 22.41 | 1300 | 5.7411          | 0.3483   | 0.3192 |
-| 0.0195        | 24.14 | 1400 | 5.7830          | 0.3501   | 0.3217 |
-| 0.0081        | 25.86 | 1500 | 5.8334          | 0.3457   | 0.3113 |
-| 0.0081        | 27.59 | 1600 | 5.7030          | 0.3532   | 0.3299 |
-| 0.0081        | 29.31 | 1700 | 5.7960          | 0.3448   | 0.3121 |
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.7241  | 100  | 1.1864          | 0.3651   | 0.3644 |
+| No log        | 3.4483  | 200  | 2.2167          | 0.3580   | 0.3355 |
+| No log        | 5.1724  | 300  | 2.7873          | 0.3673   | 0.3618 |
+| No log        | 6.8966  | 400  | 3.5495          | 0.3739   | 0.3714 |
+| 0.4197        | 8.6207  | 500  | 4.2289          | 0.3770   | 0.3708 |
+| 0.4197        | 10.3448 | 600  | 4.6578          | 0.3638   | 0.3605 |
+| 0.4197        | 12.0690 | 700  | 4.5844          | 0.3690   | 0.3671 |
+| 0.4197        | 13.7931 | 800  | 4.8103          | 0.3616   | 0.3462 |
+| 0.4197        | 15.5172 | 900  | 4.8621          | 0.3616   | 0.3545 |
+| 0.017         | 17.2414 | 1000 | 4.9407          | 0.3708   | 0.3657 |
+| 0.017         | 18.9655 | 1100 | 5.0334          | 0.3699   | 0.3696 |
+| 0.017         | 20.6897 | 1200 | 4.9701          | 0.3686   | 0.3676 |
+| 0.017         | 22.4138 | 1300 | 4.9793          | 0.3686   | 0.3654 |
+| 0.017         | 24.1379 | 1400 | 5.0299          | 0.3668   | 0.3600 |
+| 0.0076        | 25.8621 | 1500 | 5.1558          | 0.3616   | 0.3544 |
+| 0.0076        | 27.5862 | 1600 | 5.0915          | 0.3668   | 0.3622 |
+| 0.0076        | 29.3103 | 1700 | 5.0909          | 0.3682   | 0.3646 |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.44.2
 - Pytorch 2.1.1+cu121
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.19.1

config.json

@@ -39,7 +39,7 @@
   "relative_attention": true,
   "share_att_key": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.44.2",
   "type_vocab_size": 0,
   "vocab_size": 251000
 }

eval_results_cardiff.json

@@ -0,0 +1 @@
+{"arabic": {"f1": 0.3158611145225796, "accuracy": 0.31724137931034485, "confusion_matrix": [[75, 150, 65], [106, 117, 67], [99, 107, 84]]}, "english": {"f1": 0.4298847922203121, "accuracy": 0.435632183908046, "confusion_matrix": [[175, 82, 33], [137, 93, 60], [103, 76, 111]]}, "french": {"f1": 0.3133960328748027, "accuracy": 0.3195402298850575, "confusion_matrix": [[102, 134, 54], [118, 117, 55], [114, 117, 59]]}, "german": {"f1": 0.3452193841330846, "accuracy": 0.3505747126436782, "confusion_matrix": [[99, 118, 73], [109, 134, 47], [95, 123, 72]]}, "hindi": {"f1": 0.40815981127155104, "accuracy": 0.4091954022988506, "confusion_matrix": [[101, 81, 108], [81, 128, 81], [74, 89, 127]]}, "italian": {"f1": 0.3658127706962335, "accuracy": 0.3724137931034483, "confusion_matrix": [[106, 126, 58], [91, 144, 55], [96, 120, 74]]}, "portuguese": {"f1": 0.3752268719695044, "accuracy": 0.3793103448275862, "confusion_matrix": [[146, 77, 67], [142, 85, 63], [94, 97, 99]]}, "spanish": {"f1": 0.33673293917915464, "accuracy": 0.3482758620689655, "confusion_matrix": [[153, 84, 53], [147, 86, 57], [148, 78, 64]]}, "all": {"f1": 0.3629980292928143, "accuracy": 0.3646551724137931, "confusion_matrix": [[960, 833, 527], [934, 896, 490], [808, 830, 682]]}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c8945264c3f7c88891e8c8aa9600b786fb65cef1ae45a02cb64edd6dba9e50
+size 945150428

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917219b8b12a363102cf836334425bbac423bda7cd43e18580115a09e11083e2
-size 4600
+oid sha256:62a41d7c82998afd264a040f69cc3951b0b5e270e83f69a443d63e3dc25bf4db
+size 5304