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/070dd64ec90c6523_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: b2f74cd5-87c8-4e4b-92f0-2e7b449137ac
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b2f74cd5-87c8-4e4b-92f0-2e7b449137ac
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # b2f74cd5-87c8-4e4b-92f0-2e7b449137ac
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1281
 
 ## 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        | 0.0001 | 1    | 11.0493         |
+| 8.6548        | 0.0006 | 10   | 4.8534          |
+| 0.5293        | 0.0012 | 20   | 0.2472          |
+| 0.3312        | 0.0017 | 30   | 0.1316          |
+| 0.1318        | 0.0023 | 40   | 0.1259          |
+| 0.1386        | 0.0029 | 50   | 0.1281          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c3444504b2405b23448c14ab3300aa0bc5747df93d53fef5866d845fe2f973
+oid sha256:36314d63813e46a19c619223040915e8b5ed364fecb3cc765dd23e0fa46fcc65
 size 84047370