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: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/bdb71f5f780e4e12_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: ff62b1e3-2123-4deb-a5dd-455927d8055b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ff62b1e3-2123-4deb-a5dd-455927d8055b
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,8 +102,6 @@ xformers_attention: null
 # ff62b1e3-2123-4deb-a5dd-455927d8055b
 
 This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
 
 ## Model description
 
@@ -130,19 +128,14 @@ 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: 10
-- training_steps: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0000 | 1    | nan             |
-| 33.8535       | 0.0004 | 10   | nan             |
-| 11.714        | 0.0009 | 20   | nan             |
-| 8.3841        | 0.0013 | 30   | nan             |
-| 4.0994        | 0.0018 | 40   | nan             |
-| 2.9958        | 0.0022 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82d6506c79b7c3d9083e3b4b5690dce85b459bf07c653248beea7bce1521eef0
+oid sha256:16dedb1879fbf0f60e0d00efaf8e0bb4cd7a2746813637d6b010e1541fb9822a
 size 84047370