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/29364f06add4aabc_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: d39603fc-6499-4070-8632-eba5e73cd445
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: d39603fc-6499-4070-8632-eba5e73cd445
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # d39603fc-6499-4070-8632-eba5e73cd445
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8148
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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    | 1.0464          |
+| 0.8414        | 0.0013 | 10   | 1.0014          |
+| 0.7658        | 0.0025 | 20   | 0.8983          |
+| 0.7194        | 0.0038 | 30   | 0.8442          |
+| 0.7392        | 0.0050 | 40   | 0.8185          |
+| 0.8757        | 0.0063 | 50   | 0.8148          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02e8b3eef2f9ab03a7009b249466bf9690948b21355b498a8bcf7200362940a
+oid sha256:4c09abbaf0e49ff7e6572c7d178b5a36c849f2da0ff7220b756d8013708b7816
 size 84047370