End of training

README.md

@@ -67,7 +67,7 @@ lora_target_linear: true
 lr_scheduler: cosine
 max_memory:
   0: 45GB
-max_steps: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/a23c267280dd76ad_train_data.json
 model_type: AutoModelForCausalLM
@@ -94,7 +94,7 @@ wandb_name: 7e431e7a-ba1b-4142-8012-4e0289398278
 wandb_project: Gradients-On-Demand
 wandb_run: unknown
 wandb_runid: 7e431e7a-ba1b-4142-8012-4e0289398278
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -105,6 +105,8 @@ xformers_attention: null
 # 40ff6875-595b-4240-b4ef-d230c589fe9b
 
 This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -131,14 +133,19 @@ 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        | 0.0030 | 1    | nan             |
+| 0.0           | 0.0301 | 10   | nan             |
+| 0.0           | 0.0602 | 20   | nan             |
+| 0.0           | 0.0902 | 30   | nan             |
+| 0.0           | 0.1203 | 40   | nan             |
+| 0.0           | 0.1504 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59bb13828916cfcd16a7092f7ed176e457660a823eadecfb1e0afa07a2ac5bcd
+oid sha256:fded2775e9dc685eef2db2f5b104dfadabbd6f627de7f2a4c0da8ab7d5d61900
 size 17717130