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/61e360183864f5fc_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 86a90380-7ba1-47c3-ba62-640f95c2b880
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 86a90380-7ba1-47c3-ba62-640f95c2b880
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # c2ec9b66-eeeb-42a4-819e-b1e8f8426f22
 
 This model is a fine-tuned version of [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9020
 
 ## 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    | 2.7387          |
+| 6.3236        | 0.0007 | 10   | 1.4742          |
+| 4.9843        | 0.0014 | 20   | 1.0446          |
+| 3.6857        | 0.0021 | 30   | 0.9381          |
+| 5.3614        | 0.0028 | 40   | 0.9289          |
+| 3.7495        | 0.0036 | 50   | 0.9020          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0d025fd115b87aa7e130dfec3372103f1b96378e3ca3e59172f63d80fcb807
+oid sha256:c55754590a01bae103d4cde0579e21bf5ccb3d5e544b0de44b97605b20c5e545
 size 84047370