Training in progress, epoch 1

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1043
+- Loss: 0.1050
 - Accuracy: 0.9702
-- Precision: 0.6321
-- Recall: 0.6680
-- F1: 0.6496
+- Precision: 0.6561
+- Recall: 0.6741
+- F1: 0.6650
 
 ## Model description
 
@@ -45,32 +45,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| No log        | 1.0   | 26   | 0.1939          | 0.9458   | 0.0       | 0.0    | 0.0    |
-| No log        | 2.0   | 52   | 0.1404          | 0.9584   | 0.6675    | 0.5381 | 0.5958 |
-| No log        | 3.0   | 78   | 0.1218          | 0.9643   | 0.6287    | 0.6102 | 0.6193 |
-| No log        | 4.0   | 104  | 0.1090          | 0.9672   | 0.6127    | 0.6487 | 0.6302 |
-| No log        | 5.0   | 130  | 0.1049          | 0.9690   | 0.6384    | 0.6274 | 0.6329 |
-| No log        | 6.0   | 156  | 0.1013          | 0.9687   | 0.6169    | 0.6081 | 0.6125 |
-| No log        | 7.0   | 182  | 0.1030          | 0.9691   | 0.5997    | 0.6964 | 0.6444 |
-| No log        | 8.0   | 208  | 0.1067          | 0.9679   | 0.5779    | 0.7340 | 0.6467 |
-| No log        | 9.0   | 234  | 0.1058          | 0.9697   | 0.6498    | 0.6142 | 0.6315 |
-| No log        | 10.0  | 260  | 0.1043          | 0.9702   | 0.6321    | 0.6680 | 0.6496 |
+| No log        | 1.0   | 51   | 0.1397          | 0.9582   | 0.7697    | 0.4954 | 0.6028 |
+| No log        | 2.0   | 102  | 0.1134          | 0.9671   | 0.6508    | 0.6244 | 0.6373 |
+| No log        | 3.0   | 153  | 0.1069          | 0.9696   | 0.6804    | 0.6223 | 0.6501 |
+| No log        | 4.0   | 204  | 0.1059          | 0.9694   | 0.6334    | 0.6822 | 0.6569 |
+| No log        | 5.0   | 255  | 0.1050          | 0.9702   | 0.6561    | 0.6741 | 0.6650 |
 
 
 ### Framework versions
 
-- Transformers 4.53.1
+- Transformers 4.52.4
 - Pytorch 2.7.1+cu126
-- Datasets 3.6.0
-- Tokenizers 0.21.2
+- Datasets 4.0.0
+- Tokenizers 0.21.1

config.json

@@ -30,7 +30,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.53.1",
+  "transformers_version": "4.52.4",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be27b7f2e76bf0ab875a69796b8577baa21790a07767dff7e39cad0b4c0e30f
+oid sha256:cd39a1c98a12cb66d1026b4b7c76acaba1de36855c0ab171591025af23442a78
 size 1109845500

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c5728f1b899589e0ac3c02963c124cd444e1f5fe5b822308fb83f825a69acc8
-size 5713
+oid sha256:1facc5cff0491df23b0e84ef1e6cd65c2142ee7bcafe050484d31ce4fbf30556
+size 5649