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/c2630d242d385457_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: ae63dcd0-ac71-4f17-a221-7c6244b5c6eb
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ae63dcd0-ac71-4f17-a221-7c6244b5c6eb
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 9b76e7fd-f058-05f6-3b5a-5a8bf960edb9
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6375
 
 ## 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        | 0.0000 | 1    | 0.7466          |
+| 0.7084        | 0.0004 | 10   | 0.7225          |
+| 0.6795        | 0.0009 | 20   | 0.6730          |
+| 0.6638        | 0.0013 | 30   | 0.6490          |
+| 0.629         | 0.0017 | 40   | 0.6393          |
+| 0.6377        | 0.0022 | 50   | 0.6375          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79a41a57126ec30aacae1f169dbebe94cfba042299b1187aa3baaa49a7a587a
+oid sha256:136736bf1aa24cbe656ed3cbe23aca79977ef3f548819cd3921f4fdb81745d93
 size 25342042