Training in progress epoch 0

README.md

@@ -15,15 +15,16 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nlpaueb/legal-bert-small-uncased](https://huggingface.co/nlpaueb/legal-bert-small-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0147
-- Train Accuracy: 0.9962
-- Validation Loss: 0.0152
-- Validation Accuracy: 0.9964
-- Epoch: 1
+- Train Loss: 0.1528
+- Train Accuracy: 0.9651
+- Validation Loss: 0.0509
+- Validation Accuracy: 0.9914
+- Epoch: 0
 
 ## Model description
 
-This model is fine-tuned on Nifty 30-minute interval close prices from 2023-06-30T09:15:00+05:30 to 2023-09-08T15:29:00+05:30 IST. To predict the next 30-minute direction, I made a dataset where each sample contains 32 elements of z-score peak detection, which is obtained from https://stackoverflow.com/questions/22583391/peak-signal-detection-in-realtime-timeseries-data. While predicting from it, I tend to provide the last 32 elements of peak detection signal, separating them with spaces, e.g., -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0 -1.0. This is currently under development and does not guarantee optimal results.
+More information needed
+
 ## Intended uses & limitations
 
 More information needed
@@ -37,20 +38,19 @@ 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3274, '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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 608, '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 Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.0372     | 0.9932         | 0.0186          | 0.9963              | 0     |
-| 0.0147     | 0.9962         | 0.0152          | 0.9964              | 1     |
+| 0.1528     | 0.9651         | 0.0509          | 0.9914              | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
+- Transformers 4.33.2
 - TensorFlow 2.13.0
 - Datasets 2.14.5
 - Tokenizers 0.13.3

config.json

@@ -30,7 +30,7 @@
   "output_past": true,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.33.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1fef2b0959e9e8dd70fd7c20654fa4d325a16d678c9706da1ba8dc29b45718
+oid sha256:a280dea548e07490d0bd57848feef973d3a585b0c4b54912af48059b62ece449
 size 140427828