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/8d7fbafef855907a_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: dbf1257f-984b-4518-b654-372d08f639ed
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: dbf1257f-984b-4518-b654-372d08f639ed
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # dbf1257f-984b-4518-b654-372d08f639ed
 
 This model is a fine-tuned version of [unsloth/tinyllama-chat](https://huggingface.co/unsloth/tinyllama-chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4972
 
 ## Model description
 
@@ -129,13 +131,17 @@ 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: 18
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0556 | 1    | 0.6699          |
+| No log        | 0.2222 | 4    | 0.6113          |
+| No log        | 0.4444 | 8    | 0.5439          |
+| 0.6039        | 0.6667 | 12   | 0.5099          |
+| 0.6039        | 0.8889 | 16   | 0.4972          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7a7212c5ef97f288fcf7c623a7b78c36f80cc8bd7365bb9c6c5a1cc944d032
+oid sha256:3668452cb890e30f5d46ebe1aaf5e30076cfb36d6a23c6b0cf6c1c1306b2fb1f
 size 25342042