End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 1
+max_steps: 50
 micro_batch_size: 8
 mlflow_experiment_name: /tmp/09500df8146c2da1_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 8dfad597-307b-41c0-8cb9-c6935ff8a419
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 8dfad597-307b-41c0-8cb9-c6935ff8a419
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 8dfad597-307b-41c0-8cb9-c6935ff8a419
 
 This model is a fine-tuned version of [unsloth/llama-2-7b](https://huggingface.co/unsloth/llama-2-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0420
 
 ## Model description
 
@@ -129,13 +131,18 @@ 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: 2
-- training_steps: 1
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0080 | 1    | 8.0571          |
+| 5.3726        | 0.0800 | 10   | 1.1352          |
+| 0.6489        | 0.1599 | 20   | 0.3798          |
+| 0.2278        | 0.2399 | 30   | 0.0655          |
+| 0.0748        | 0.3198 | 40   | 0.0472          |
+| 0.0422        | 0.3998 | 50   | 0.0420          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4df3782f17caeefc316cf24a5bdbabbbee9adcc69697aa12c2ddac78f29852
+oid sha256:ef05c0aab746d1e026e3fc73b1465f41a7ddd94194dbfa060f7eac69e1e352f5
 size 80115210