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/92268f6108266d1e_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # f5ef386f-d229-4165-8b6e-c7cdfbe5f69a
 
 This model is a fine-tuned version of [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0275
 
 ## 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        | 0.0000 | 1    | 1.2712          |
+| No log        | 0.0000 | 1    | 1.2713          |
+| 0.9698        | 0.0001 | 10   | 0.6087          |
+| 0.1668        | 0.0003 | 20   | 0.0934          |
+| 0.0561        | 0.0004 | 30   | 0.0429          |
+| 0.0305        | 0.0005 | 40   | 0.0290          |
+| 0.0191        | 0.0006 | 50   | 0.0275          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550e8b4ec5a6535041a8dca3e57f09ebec5bdd9c17a1562600de4819633bad70
+oid sha256:1a10f110300ea17bb2239f10032b99a65b40d69aa7368939f0addc67b5104e94
 size 604420306