End of training

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: roberta-base
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my-roberta-for-hateful-meme-classification
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6919
+- Loss: 0.6894
 
 ## Model description
 
@@ -36,23 +36,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4823        | 1.0   | 1611 | 0.6919          |
-| 0.4609        | 2.0   | 3222 | 0.7319          |
-| 0.3615        | 3.0   | 4833 | 0.6982          |
-| 0.3616        | 4.0   | 6444 | 0.7132          |
-| 0.5695        | 5.0   | 8055 | 0.7753          |
+| 0.5181        | 1.0   | 806  | 0.7357          |
+| 0.5235        | 2.0   | 1612 | 0.7480          |
+| 0.4906        | 3.0   | 2418 | 0.7239          |
+| 0.4673        | 4.0   | 3224 | 0.7252          |
+| 0.4678        | 5.0   | 4030 | 0.6894          |
+| 0.4481        | 6.0   | 4836 | 0.7794          |
+| 0.4038        | 7.0   | 5642 | 0.7926          |
+| 0.3052        | 8.0   | 6448 | 0.9150          |
+| 0.2344        | 9.0   | 7254 | 1.1734          |
+| 0.271         | 10.0  | 8060 | 1.1404          |
 
 
 ### Framework versions

logs/events.out.tfevents.1726988361.c84b18c87752.1607.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1941a7b0064dceac354fbc9fed2499f5415ff6aad02e7ef67883e989bfbfdb3d
-size 91471
+oid sha256:1d6ddbc3487b79251f0bc02cd76f50581c5ce37b2831eae361f082108a9b6efc
+size 178213

logs/events.out.tfevents.1726994821.c84b18c87752.1607.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cfc0a4f9c0217fd85ba9c016cf93b4db2b33f1fcc2795bc1af92fd5e9e4b58
+size 359

tokenizer_config.json

@@ -4,7 +4,7 @@
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,12 +28,12 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "250001": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260