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/a706891cfe3c8578_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 4967c5c6-763a-40de-b261-7a9b4ee1dbdf
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4967c5c6-763a-40de-b261-7a9b4ee1dbdf
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # b176244e-5bd9-0db1-7c95-e54596fc49b3
 
 This model is a fine-tuned version of [echarlaix/tiny-random-PhiForCausalLM](https://huggingface.co/echarlaix/tiny-random-PhiForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.9353
 
 ## 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    | 6.9401          |
+| 6.9437        | 0.0005 | 10   | 6.9393          |
+| 6.9351        | 0.0009 | 20   | 6.9375          |
+| 6.9387        | 0.0014 | 30   | 6.9361          |
+| 6.9363        | 0.0018 | 40   | 6.9355          |
+| 6.9322        | 0.0023 | 50   | 6.9353          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f5370cefe8df629f175327aa7e46d4229dd2909c3154be418e5afb531151d3
+oid sha256:2d1c835c000f36005ba7d3089d9c02325fd4ce5493900ff8a46bc6bac30a34b1
 size 168063