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/7ad07d8419e9ecf3_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: dc5a7882-843e-4bae-a952-d8ceb228de29
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: dc5a7882-843e-4bae-a952-d8ceb228de29
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # dc5a7882-843e-4bae-a952-d8ceb228de29
 
 This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
 
 ## 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: 34
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0299 | 1    | 3.9087          |
+| No log        | 0.2093 | 7    | 0.4576          |
+| 27.8654       | 0.4187 | 14   | 0.0000          |
+| 0.0024        | 0.6280 | 21   | 0.0000          |
+| 0.0024        | 0.8374 | 28   | 0.0000          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f7d896d59fa5a5c7d04e4da4bfc512bcf7031e3354cb946b93e0e4dd4b37ab
+oid sha256:e93a4c66040d0225f1856eb625b8961f369aab8cde62b7128858336c11b8bd94
 size 84047370