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/3366ce729456880b_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 45ea4051-757d-4149-834c-b117e93c4b4c
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 45ea4051-757d-4149-834c-b117e93c4b4c
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 45ea4051-757d-4149-834c-b117e93c4b4c
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3013
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0021 | 1    | 9.1468          |
+| 7.8659        | 0.0215 | 10   | 6.6159          |
+| 3.4119        | 0.0430 | 20   | 2.6910          |
+| 1.7896        | 0.0644 | 30   | 1.6870          |
+| 1.9569        | 0.0859 | 40   | 1.3932          |
+| 1.3353        | 0.1074 | 50   | 1.3013          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3580a9ce3ee296dc9ab5f1223903f9c0c323c466b4b50cbd907214ea84dd43
+oid sha256:31df37bfb9b179975d87acfbd368d53b2dd5cf6194c5a61bda99440cb2013d9f
 size 25342042