End of training

README.md

@@ -1,13 +1,10 @@
 ---
-library_name: peft
+library_name: transformers
 license: apache-2.0
 base_model: unsloth/orpheus-3b-0.1-pretrained
 tags:
-- base_model:adapter:unsloth/orpheus-3b-0.1-pretrained
-- lora
-- transformers
 - unsloth
-pipeline_tag: text-generation
+- generated_from_trainer
 model-index:
 - name: nyiha_nt-tts-lora
   results: []
@@ -43,7 +40,7 @@ The following hyperparameters were used during training:
 - seed: 3407
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
-- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
 - num_epochs: 5.0
@@ -54,8 +51,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.16.0
-- Transformers 4.53.2
+- Transformers 4.53.3
 - Pytorch 2.7.1+cu126
 - Datasets 4.0.0
-- Tokenizers 0.21.2
+- Tokenizers 0.21.2

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128009,
+  "max_length": 131072,
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.53.3"
+}

tokenizer_config.json

@@ -231535,7 +231535,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }