End of training

README.md

@@ -1,11 +1,11 @@
 ---
+library_name: transformers
 license: other
-library_name: peft
+base_model: deepseek-ai/deepseek-coder-1.3b-base
 tags:
 - trl
 - kto
 - generated_from_trainer
-base_model: deepseek-ai/deepseek-coder-1.3b-base
 model-index:
 - name: kto_test
   results: []
@@ -35,21 +35,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.41e-05
+- learning_rate: 0.1
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 16
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_steps: 200
 - num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.42.0.dev0
-- Pytorch 2.2.2+cu121
-- Datasets 2.19.0
-- Tokenizers 0.19.1
+- Transformers 4.45.0
+- Pytorch 2.5.1+cu124
+- Datasets 2.19.2
+- Tokenizers 0.20.3

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.45.0"
+}