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/cb779b9088d7bb41_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 8ea16bb1-ca3a-4ab7-81e3-e702e2663f5d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 8ea16bb1-ca3a-4ab7-81e3-e702e2663f5d
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 0f4fde92-839c-4c46-8511-eb7131dadfcc
 
 This model is a fine-tuned version of [unsloth/mistral-7b](https://huggingface.co/unsloth/mistral-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7658
 
 ## Model description
 
@@ -127,14 +129,17 @@ 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: 4
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.2857 | 1    | 0.7664          |
+| No log        | 0.5714 | 2    | 0.7672          |
+| No log        | 0.8571 | 3    | 0.7667          |
+| No log        | 1.1429 | 4    | 0.7658          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1f075f7d0171d9101062ca243336e811e7f8a16f9769e58d7515afc75c25e8
+oid sha256:64bb307dd557d2118fd2273f206f8133d0d6a640da39317f047c2407ea7848e0
 size 84047370