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/7c327f63dae0649f_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 6a053134-ea65-47c0-9030-2665fdacbc13
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 6a053134-ea65-47c0-9030-2665fdacbc13
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 6a053134-ea65-47c0-9030-2665fdacbc13
 
 This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0159
 
 ## 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    | 3.7623          |
+| 13.6618       | 0.0014 | 10   | 3.3053          |
+| 12.3206       | 0.0027 | 20   | 3.0396          |
+| 12.1189       | 0.0041 | 30   | 3.0245          |
+| 12.2395       | 0.0055 | 40   | 3.0223          |
+| 12.1334       | 0.0068 | 50   | 3.0159          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbe13f5a7c4ec3358d9c085a0e085745d1af3465e11fe89b735b4a14fbdce06
+oid sha256:a58d66b2a61532406ca4dc47c205d5e366dadafb6090548da77c72acf34c85a4
 size 84047370