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: 8
 mlflow_experiment_name: /tmp/566683be083d637a_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 3cd47837-991c-4ba6-b979-c22f8e5b5bac
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3cd47837-991c-4ba6-b979-c22f8e5b5bac
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 3cd47837-991c-4ba6-b979-c22f8e5b5bac
 
 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: 0.5688
 
 ## Model description
 
@@ -131,13 +133,18 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0010 | 1    | 9.6364          |
+| 7.9513        | 0.0102 | 10   | 5.1132          |
+| 2.949         | 0.0204 | 20   | 1.1615          |
+| 0.8331        | 0.0306 | 30   | 0.6371          |
+| 0.5964        | 0.0408 | 40   | 0.5855          |
+| 0.5797        | 0.0509 | 50   | 0.5688          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56fa7bd93a4f2e9348d91e38c26ebcc00f6f5b42c46dd66ca6efdff8bbc245e7
+oid sha256:eb083e6e59bcb7156a043d6922ca32f8b61103b89a6724b0797ff2449454a08e
 size 25342042