Training in progress epoch 0

README.md

@@ -1,22 +1,24 @@
 ---
-base_model: AhsenKacar/TurkishReviews-ds-mini
 library_name: transformers
 license: mit
+base_model: gpt2
 tags:
 - generated_from_keras_callback
 model-index:
-- name: TurkishReviews-ds-mini
+- name: AhsenKacar/TurkishReviews-ds-mini
   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. -->
 
-# TurkishReviews-ds-mini
+# AhsenKacar/TurkishReviews-ds-mini
 
-This model is a fine-tuned version of [AhsenKacar/TurkishReviews-ds-mini](https://huggingface.co/AhsenKacar/TurkishReviews-ds-mini) on an unknown dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-
+- Train Loss: 8.7685
+- Validation Loss: 7.6386
+- Epoch: 0
 
 ## Model description
 
@@ -35,11 +37,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': -998, '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}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 43, '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
 
 ### Training results
 
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 8.7685     | 7.6386          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "AhsenKacar/TurkishReviews-ds-mini",
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -34,5 +34,5 @@
   },
   "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 44208
+  "vocab_size": 52000
 }

special_tokens_map.json

@@ -13,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:021f21f66b68414a34de686180afc76d171f6203a85a2d3a06a81a976317eab9
-size 479352912
+oid sha256:a0f55340b50784449b5cf6d58607c29975f4641942b787618d8091c31e7a792f
+size 503289936

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 40,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -16,7 +16,7 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": null,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }