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/8e5949ee9dae7200_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: bbbd1a27-07a3-4c42-ab68-a7f0b1657031
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: bbbd1a27-07a3-4c42-ab68-a7f0b1657031
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 6753df6b-eab9-4280-a440-2cefb8252d95
 
 This model is a fine-tuned version of [echarlaix/tiny-random-mistral](https://huggingface.co/echarlaix/tiny-random-mistral) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3748
 
 ## 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    | 10.3774         |
+| 41.5087       | 0.0003 | 10   | 10.3770         |
+| 41.5029       | 0.0006 | 20   | 10.3760         |
+| 41.5015       | 0.0008 | 30   | 10.3753         |
+| 41.4964       | 0.0011 | 40   | 10.3749         |
+| 41.507        | 0.0014 | 50   | 10.3748         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f2d971f998b4edc47fae5a00aacd6f22bc21d57f7b63c3b7a766a36ee6efbcb
+oid sha256:0307112c071a1ad878332ada7e114040f9f1b29288c6a7bbe1e6a0634946a1d5
 size 37506