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/1fb9d0f1383609cd_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: dea3b495-abf1-42df-9336-f1358c9fa838
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: dea3b495-abf1-42df-9336-f1358c9fa838
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 1d6fb26e-7efa-4d09-9133-23dc78cfc27b
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4882
 
 ## 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    | 4.6060          |
+| 4.2717        | 0.0007 | 10   | 3.6619          |
+| 1.9359        | 0.0014 | 20   | 1.5537          |
+| 0.9317        | 0.0021 | 30   | 0.7600          |
+| 0.4957        | 0.0027 | 40   | 0.5292          |
+| 0.4898        | 0.0034 | 50   | 0.4882          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c6fa93ab10d40d9e14bcb7952a1411aa18eb26d9db7cfce2debd4785767700
+oid sha256:8e5be70a96a352a5d99be0c465eff89bd69d5bede609347bb4852085c069f4d5
 size 80881450