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/0ce1651f3f151eb3_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: cffdc7a8-b56c-478f-8c74-5070036720d8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: cffdc7a8-b56c-478f-8c74-5070036720d8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 795046e9-ae53-63ac-957e-73f11de8bff9
 
 This model is a fine-tuned version of [migtissera/Tess-v2.5-Phi-3-medium-128k-14B](https://huggingface.co/migtissera/Tess-v2.5-Phi-3-medium-128k-14B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7434
 
 ## 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        | 0.0002 | 1    | 4.0329          |
+| 16.1186       | 0.0023 | 10   | 3.8768          |
+| 11.016        | 0.0046 | 20   | 2.3920          |
+| 7.0602        | 0.0069 | 30   | 1.8660          |
+| 7.616         | 0.0091 | 40   | 1.7592          |
+| 7.2517        | 0.0114 | 50   | 1.7434          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1441fd415f5f8272390280fecc0f23d0af514446cb574344ce19273d38f012
+oid sha256:9cc40aa9f47cf89aa7904acc9212602260d71f135f4aabd637bd9b0f4537e29a
 size 111526858