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/63c09d257de4ad38_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 629f4f71-3b70-43e5-9b7c-dc2d949d68a4
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 629f4f71-3b70-43e5-9b7c-dc2d949d68a4
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 629f4f71-3b70-43e5-9b7c-dc2d949d68a4
 
 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: 10.9570
 
 ## 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: 18
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0565 | 1    | 11.0906         |
+| No log        | 0.2261 | 4    | 11.0552         |
+| No log        | 0.4523 | 8    | 11.0073         |
+| 176.7641      | 0.6784 | 12   | 10.9721         |
+| 176.7641      | 0.9046 | 16   | 10.9570         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7929e4c05c8ba2a099944256a9e5167b988b6b325fd0c0130154f321ada0883
+oid sha256:e2b7bd7efde283f049fc12de2d5633a66c24e980d4615c5e3d6fa6a69607d0d4
 size 129182