Training in progress epoch 0

README.md

@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.7583
-- Train End Logits Accuracy: 0.5813
-- Train Start Logits Accuracy: 0.5573
-- Validation Loss: 2.0446
-- Validation End Logits Accuracy: 0.5277
-- Validation Start Logits Accuracy: 0.4928
-- Epoch: 1
+- Train Loss: 2.3715
+- Train End Logits Accuracy: 0.5054
+- Train Start Logits Accuracy: 0.4994
+- Validation Loss: 2.0790
+- Validation End Logits Accuracy: 0.5204
+- Validation Start Logits Accuracy: 0.4818
+- Epoch: 0
 
 ## Model description
 
@@ -40,20 +40,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4524, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 45240, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
-| 2.3577     | 0.5055                    | 0.4987                      | 2.1050          | 0.5151                         | 0.4843                           | 0     |
-| 1.7583     | 0.5813                    | 0.5573                      | 2.0446          | 0.5277                         | 0.4928                           | 1     |
+| 2.3715     | 0.5054                    | 0.4994                      | 2.0790          | 0.5204                         | 0.4818                           | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.40.1
+- Transformers 4.39.3
 - TensorFlow 2.15.0
-- Datasets 2.19.0
-- Tokenizers 0.19.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -19,6 +19,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.39.3",
   "vocab_size": 28996
 }

logs/train/events.out.tfevents.1714957848.f7da57357404.85.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3640efc651edb68691bf6e81958f820c41ded334e9d2afd2d88d97a05cde6cb3
+size 1441432

logs/validation/events.out.tfevents.1714958638.f7da57357404.85.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7fecf2d0a13e69cbc9eff529faa0e91a56780080b12a3800942ad9391d55cd
+size 604

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed50b783f2104f5ed6df36aca4f5bfdf4e10160233e841b5ab405e938b6a1867
+oid sha256:1c6dfd63deb1ef336849e61d8886a36975c4abf646ec62bd2ed97bcf33b93587
 size 260895720

tokenizer_config.json

@@ -45,7 +45,7 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,