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/a26a8dba741b4ca1_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 2cc9a107-3883-49d9-bae4-0b2c1ea759f6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2cc9a107-3883-49d9-bae4-0b2c1ea759f6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 71f0a9d5-e3c5-4a42-bdd5-fff7e24c7f7a
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4382
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0105 | 1    | 5.7820          |
+| 4.9436        | 0.1053 | 10   | 4.7803          |
+| 3.2459        | 0.2105 | 20   | 3.2652          |
+| 2.7367        | 0.3158 | 30   | 2.6135          |
+| 2.3017        | 0.4211 | 40   | 2.4747          |
+| 2.4422        | 0.5263 | 50   | 2.4382          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6562ed5a013c186a6f7e403f9e24425bc2cd8134e4559ae0ac2c135f6a61cabc
+oid sha256:40a9b7060961825a7db4a0da1c6b8eef0ad787b703708b776746e0fa07363766
 size 25342042