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/e00163d96cc6bc67_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 4241bc8f-55c8-488f-8a10-8f9c3ac74668
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4241bc8f-55c8-488f-8a10-8f9c3ac74668
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 5d127683-e605-40fd-88eb-be3c833b2332
 
 This model is a fine-tuned version of [unsloth/llama-2-7b-chat](https://huggingface.co/unsloth/llama-2-7b-chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3919
 
 ## 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        | 0.0037 | 1    | 2.6254          |
+| 2.6056        | 0.0371 | 10   | 2.5287          |
+| 2.434         | 0.0743 | 20   | 2.4431          |
+| 2.4991        | 0.1114 | 30   | 2.4090          |
+| 2.4061        | 0.1486 | 40   | 2.3941          |
+| 2.3304        | 0.1857 | 50   | 2.3919          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a304671fddc5d0811c5fd32e0f24f2e1a073f0f41f0069f184a14b3b659530
+oid sha256:0d01cb3ec88884ca26ba8651148390dcd083b2b8a3897b079b4a0cecc7351d04
 size 80115210