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/142d1caf7e37d8d8_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: f6275232-6f51-4c93-a4e5-51ed8fd4f747
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f6275232-6f51-4c93-a4e5-51ed8fd4f747
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # f6275232-6f51-4c93-a4e5-51ed8fd4f747
 
 This model is a fine-tuned version of [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0708
 
 ## 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    | 6.9004          |
+| 10.7889       | 0.0008 | 10   | 1.4553          |
+| 1.414         | 0.0017 | 20   | 0.2693          |
+| 0.2817        | 0.0025 | 30   | 0.0794          |
+| 0.2428        | 0.0034 | 40   | 0.0917          |
+| 0.3502        | 0.0042 | 50   | 0.0708          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af5037041fa3f0b6b102f913cd15876f3cf7d54cf1264ec5c729962d1ced309
+oid sha256:d0d09531e74ad5e6372eb89039318bd043c05e9bda264f998e7572b33cf239fd
 size 84047370