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: 8
 mlflow_experiment_name: /tmp/55a8d7a2c827f322_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: e398d279-63ec-4d67-bfce-df769d9cb75a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e398d279-63ec-4d67-bfce-df769d9cb75a
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # e398d279-63ec-4d67-bfce-df769d9cb75a
 
 This model is a fine-tuned version of [katuni4ka/tiny-random-falcon-40b](https://huggingface.co/katuni4ka/tiny-random-falcon-40b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.0090
 
 ## Model description
 
@@ -130,13 +132,17 @@ 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: 43
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0236 | 1    | 11.2170         |
+| No log        | 0.2124 | 9    | 11.1658         |
+| 179.1345      | 0.4248 | 18   | 11.0909         |
+| 177.9139      | 0.6372 | 27   | 11.0314         |
+| 176.7675      | 0.8496 | 36   | 11.0090         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145255058cf5c7a622af275f2211079383557310f9bf0ec909763ee8864145c9
+oid sha256:280ef16a964011d4cf6d7dd985608657743f847537f2d26695679d57ae3faef7
 size 129182