End of training

README.md

@@ -64,7 +64,7 @@ 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/3547704a22c5b5a5_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 8a27943e-4c32-44a9-b580-9571b022d880
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 8a27943e-4c32-44a9-b580-9571b022d880
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 8a27943e-4c32-44a9-b580-9571b022d880
 
 This model is a fine-tuned version of [fxmarty/tiny-llama-fast-tokenizer](https://huggingface.co/fxmarty/tiny-llama-fast-tokenizer) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3158
 
 ## 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        | 0.0001 | 1    | 10.3366         |
+| 10.3331       | 0.0012 | 10   | 10.3332         |
+| 10.3252       | 0.0023 | 20   | 10.3255         |
+| 10.3203       | 0.0035 | 30   | 10.3195         |
+| 10.3154       | 0.0047 | 40   | 10.3163         |
+| 10.3136       | 0.0059 | 50   | 10.3158         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241d5683ff72637324779991bd9688a9d97d6ca5d3921faacf9080b9b333c7bc
+oid sha256:f9e59b28ff5f4fff609ee6b4b2fa1277f90c9b0dd53c1abbcbf135f8b2df1a5d
 size 33666