Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1696
-- Validation Loss: 1.1571
-- Train Accuracy: 0.6723
-- Epoch: 3
+- Train Loss: 1.1841
+- Validation Loss: 1.4953
+- Train Accuracy: 0.5085
+- Epoch: 0
 
 ## Model description
 
@@ -36,22 +36,19 @@ 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 788, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 597, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.1664     | 1.2814          | 0.5723         | 0     |
-| 0.3526     | 1.1862          | 0.6766         | 1     |
-| 0.2239     | 1.1143          | 0.6915         | 2     |
-| 0.1696     | 1.1571          | 0.6723         | 3     |
+| 1.1841     | 1.4953          | 0.5085         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.27.4
-- TensorFlow 2.11.0
-- Datasets 2.11.0
-- Tokenizers 0.13.3
+- Transformers 4.24.0
+- TensorFlow 2.10.0
+- Datasets 2.10.1
+- Tokenizers 0.11.0

config.json

@@ -44,6 +44,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.24.0",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415c90e7f9810084581b75e1f2a35825381d272b22c3814f0eaed2a5b220f29c
-size 267979456
+oid sha256:9ad5cc1b6a6047ea60b909abf2c1b173d8bd92e43f4b78ebd22aa4e85847e48e
+size 267982792

tokenizer.json

@@ -10,48 +10,48 @@
   "added_tokens": [
     {
       "id": 0,
+      "special": true,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": false
     },
     {
       "id": 100,
+      "special": true,
       "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": false
     },
     {
       "id": 101,
+      "special": true,
       "content": "[CLS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": false
     },
     {
       "id": 102,
+      "special": true,
       "content": "[SEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": false
     },
     {
       "id": 103,
+      "special": true,
       "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -3,6 +3,7 @@
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,