End of training

README.md

@@ -65,7 +65,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/e15b312fcffd2092_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 1931d421-be92-4862-862f-898a7a812884
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 1931d421-be92-4862-862f-898a7a812884
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 1931d421-be92-4862-862f-898a7a812884
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5590
 
 ## Model description
 
@@ -127,14 +129,19 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 8
 - 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: 2
-- training_steps: 1
+- lr_scheduler_warmup_steps: 10
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0006 | 1    | 0.9079          |
+| 0.8808        | 0.0063 | 10   | 0.8240          |
+| 0.7148        | 0.0127 | 20   | 0.6664          |
+| 0.613         | 0.0190 | 30   | 0.5932          |
+| 0.5633        | 0.0253 | 40   | 0.5639          |
+| 0.5545        | 0.0316 | 50   | 0.5590          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e410a475cd9b012166b1b8f030b9fc378b52e6271b940360279abc3195a3e3a
+oid sha256:30102efbaae89ac3ad1c2fd5e62a000d66ffc18bc78966d139cce7bb9e9d7997
 size 80881450