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/6647406ddfc023c8_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: ed9f33b9-8114-47d5-b3b4-199970538cf4
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ed9f33b9-8114-47d5-b3b4-199970538cf4
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # de44363b-1544-49f6-86e7-c7aec3410086
 
 This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0289
 
 ## 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        | 0.0000 | 1    | 0.3170          |
+| 0.2509        | 0.0001 | 10   | 0.2066          |
+| 0.076         | 0.0003 | 20   | 0.0489          |
+| 0.0624        | 0.0004 | 30   | 0.0336          |
+| 0.0201        | 0.0006 | 40   | 0.0294          |
+| 0.0319        | 0.0007 | 50   | 0.0289          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e7420bbfb23185b26dd0eb7a3ebb0ad54a0fbd4b46d4a1fcb930dc47dc3e9f
+oid sha256:3c2720e57be0ff0daf6eea271a1414eaa718ed10a73d5eab18fe45605e956672
 size 30103498