Training in progress epoch 0

README.md

@@ -5,15 +5,6 @@ tags:
 model-index:
 - name: kmkarakaya/turkishReviews-ds
   results: []
-widget:
-- text: "Aldığım üründe çıkan arıza"
-  example_title: "Example 1"
-- text: "Çağrı merkezini aradım."
-  example_title: "Example 2"
-- text: "Uçak biletini değiştirmek istedim ama"
-  example_title: "Example 3"
-- text: "Ürün değiştirmek için"
-  example_title: "Example 4"
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
@@ -23,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 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: 4.5744
-- Validation Loss: 4.5366
-- Epoch: 2
+- Train Loss: 5.5525
+- Validation Loss: 5.5251
+- Epoch: 0
 
 ## Model description
 
@@ -44,16 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 11152, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 10304, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, '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 |
 |:----------:|:---------------:|:-----:|
-| 4.5746     | 4.5366          | 0     |
-| 4.5745     | 4.5366          | 1     |
-| 4.5744     | 4.5366          | 2     |
+| 5.5525     | 5.5251          | 0     |
 
 
 ### Framework versions

config.json

@@ -5,9 +5,9 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50257,
+  "bos_token_id": 0,
   "embd_pdrop": 0.1,
-  "eos_token_id": 50257,
+  "eos_token_id": 0,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -34,5 +34,5 @@
   },
   "transformers_version": "4.20.1",
   "use_cache": true,
-  "vocab_size": 50258
+  "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 sha256:72d3c5ab5a37ca1806d0e290f962f393922cc8371c4630a313344981faf9aef6
-size 497937992
+oid sha256:de0733103ad190d49f552fa92fa0a98cbaf112f76d9412f60551dba2af6dd1ff
+size 503289416

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

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 1024,
-  "name_or_path": "redrussianarmy/gpt2-turkish-cased",
+  "name_or_path": "kmkarakaya/turkishReviews-ds",
   "pad_token": null,
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",