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: 8
 mlflow_experiment_name: /tmp/bb93f37edd760ff3_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: 5bb15199-bfd7-4a20-bcce-8ddcac758358
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5bb15199-bfd7-4a20-bcce-8ddcac758358
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # 5bb15199-bfd7-4a20-bcce-8ddcac758358
 
 This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3537
 
 ## Model description
 
@@ -127,13 +129,18 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0027 | 1    | 10.3727         |
+| 10.3703       | 0.0269 | 10   | 10.3666         |
+| 10.3636       | 0.0539 | 20   | 10.3603         |
+| 10.3582       | 0.0808 | 30   | 10.3560         |
+| 10.3546       | 0.1078 | 40   | 10.3540         |
+| 10.3534       | 0.1347 | 50   | 10.3537         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9866d36ff30923a631b2d4875ccbf13d5d9add2b29cecf14f119db472ff2785e
+oid sha256:60bdf95b1520af28c2d450064081309684feea60dc832bafc11da84f14373916
 size 33666