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: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/bf757ffa84b69032_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 5dc1feaf-f400-43b3-bd1e-e3ef711ec973
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5dc1feaf-f400-43b3-bd1e-e3ef711ec973
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # af303489-9a36-408d-bbec-ef0fe307d5be
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2307
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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        | 0.0038 | 1    | 2.3726          |
+| 1.5694        | 0.0380 | 10   | 1.1096          |
+| 0.4531        | 0.0760 | 20   | 0.4471          |
+| 0.2537        | 0.1141 | 30   | 0.2731          |
+| 0.3914        | 0.1521 | 40   | 0.2599          |
+| 0.1591        | 0.1901 | 50   | 0.2307          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7598a81abcfbb1b9305df5d4d16956902164e002d1382ec22ba2173ea1a4cc5a
+oid sha256:9e0a918c432375eccfc06341e9cbc499d60abdb1342e53643e3de99c54c58338
 size 84047370