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: 2
 mlflow_experiment_name: /tmp/2f1591347bf2ff02_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 0784bd1f-31e8-4849-b800-e6b9b1ce831f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0784bd1f-31e8-4849-b800-e6b9b1ce831f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # a8596733-36e5-6c1b-29d1-cff7d7dbb128
 
 This model is a fine-tuned version of [unsloth/OpenHermes-2.5-Mistral-7B](https://huggingface.co/unsloth/OpenHermes-2.5-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3076
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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        | 0.0003 | 1    | 1.1513          |
+| 3.4863        | 0.0028 | 10   | 0.6390          |
+| 1.6406        | 0.0057 | 20   | 0.3515          |
+| 1.2326        | 0.0085 | 30   | 0.3193          |
+| 1.2825        | 0.0113 | 40   | 0.3097          |
+| 1.1455        | 0.0141 | 50   | 0.3076          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f3a8fced748de10234f13eb718d93a2673b04ba6ada320ae930ddb2b6af603
+oid sha256:4d45e27d27ac1a392309a80f9f8fcf4ec344f25ae980603b6b7f3f980146a8c4
 size 84047370