End of training

README.md

@@ -69,7 +69,8 @@ lora_r: 128
 lora_target_linear: true
 lr_scheduler: cosine
 max_grad_norm: 1.0
-max_steps: 300
+max_steps: 600
+auto_resume_from_checkpoints: true
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/000dac3a8cb81c80_train_data.json
 model_type: AutoModelForCausalLM
@@ -106,7 +107,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5562
+- Loss: 0.5509
 
 ## Model description
 
@@ -134,7 +135,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- training_steps: 300
+- training_steps: 600
 
 ### Training results
 
@@ -147,6 +148,12 @@ The following hyperparameters were used during training:
 | 0.507         | 0.0224 | 200  | 0.5608          |
 | 0.5901        | 0.0280 | 250  | 0.5569          |
 | 0.5583        | 0.0336 | 300  | 0.5562          |
+| 0.6019        | 0.0392 | 350  | 0.5567          |
+| 0.5378        | 0.0448 | 400  | 0.5553          |
+| 0.4796        | 0.0504 | 450  | 0.5526          |
+| 0.5788        | 0.0560 | 500  | 0.5517          |
+| 0.5497        | 0.0616 | 550  | 0.5511          |
+| 0.5998        | 0.0672 | 600  | 0.5509          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df4bee64edf2323611d04f90ff07ca6cd9258b1028dc07f8c8ae1df76e3a7b7
+oid sha256:b087a55fbe8c06647f39ce4ff1f96316857798019ecce7603f7d32036343eab1
 size 591014186