End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/2d001c3aa53c3830_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: e7a8e2dd-1c3c-47b1-96ef-f26e57a22615
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e7a8e2dd-1c3c-47b1-96ef-f26e57a22615
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,8 +102,6 @@ xformers_attention: null
 # e7a8e2dd-1c3c-47b1-96ef-f26e57a22615
 
 This model is a fine-tuned version of [unsloth/codegemma-7b-it](https://huggingface.co/unsloth/codegemma-7b-it) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1446
 
 ## Model description
 
@@ -130,19 +128,14 @@ 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: 10
-- training_steps: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0007 | 1    | 10.5528         |
-| 7.7488        | 0.0071 | 10   | 4.3914          |
-| 0.5001        | 0.0142 | 20   | 0.4179          |
-| 0.3107        | 0.0212 | 30   | 0.2178          |
-| 0.1783        | 0.0283 | 40   | 0.1497          |
-| 0.3288        | 0.0354 | 50   | 0.1446          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc236cc2200e43f71ba7505c58e32fb229c5ab5ac15f69e253236b4daa63b0c
+oid sha256:538bac8e466f80a84e3f91c85a6650c958b72c440d2306382e7c1af96d670e21
 size 100149034