End of training

README.md

@@ -2,22 +2,20 @@
 license: apache-2.0
 base_model: distilbert-base-uncased
 tags:
-- generated_from_keras_callback
+- generated_from_trainer
 model-index:
-- name: dsfdsf2/distilbert-base-uncased-finetuned-imdb
+- name: distilbert-base-uncased-finetuned-imdb
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-# dsfdsf2/distilbert-base-uncased-finetuned-imdb
+# distilbert-base-uncased-finetuned-imdb
 
 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: 2.8555
-- Validation Loss: 2.5960
-- Epoch: 0
+- Loss: 2.4894
 
 ## Model description
 
@@ -36,19 +34,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -688, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
-- training_precision: mixed_float16
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 2.8555     | 2.5960          | 0     |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.6819        | 1.0   | 157  | 2.4978          |
+| 2.5872        | 2.0   | 314  | 2.4488          |
+| 2.527         | 3.0   | 471  | 2.4823          |
 
 
 ### Framework versions
 
 - Transformers 4.40.2
-- TensorFlow 2.15.0
+- Pytorch 2.2.1+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -18,6 +18,7 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
+  "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df93f3b2c9b240d47ef5b704507ecd15f2ac6bd6df8ab923b6e68f098c580bc6
+size 267954768

runs/May11_18-12-42_cb4c088d8c3b/events.out.tfevents.1715451220.cb4c088d8c3b.168.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41814194e611e09901fbc35e9b4660960bf5e3e7cccb99f2d21ddc7d883927b1
+size 6626

runs/May11_18-12-42_cb4c088d8c3b/events.out.tfevents.1715451674.cb4c088d8c3b.168.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3ae4692e05b313eccb03f34c93fb343e1e040d83b3d8427ca6a18bf6c9d019
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce432645a7928d923c09ba7a782fb7236e57f0e238f845c70022ff68f1ddbc34
+size 5048