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/e8b692eedd774c6f_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 3e8f3f4e-67d5-4150-b6fb-f7b5e935792a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3e8f3f4e-67d5-4150-b6fb-f7b5e935792a
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 5c382791-b6f9-4813-ab70-93488a2fa908
 
 This model is a fine-tuned version of [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4010
 
 ## 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        | 0.0021 | 1    | 1.3077          |
+| No log        | 0.0021 | 1    | 1.3076          |
+| 1.1535        | 0.0211 | 10   | 1.0952          |
+| 0.5502        | 0.0421 | 20   | 0.5695          |
+| 0.4126        | 0.0632 | 30   | 0.4491          |
+| 0.4188        | 0.0843 | 40   | 0.4099          |
+| 0.4902        | 0.1054 | 50   | 0.4010          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c06d3eab8aa0e5adcdb44b7c71d4967cd790a5c3e90262becf6cd6e72913404
+oid sha256:2b5781835ab9f7c503626c78d8c94b8b4acdc6c881a228e6bd71fd8ab51c4559
 size 604420306