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/4610b9353986c162_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: e70fec0d-c949-48ee-aa83-df5ca1800db5
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e70fec0d-c949-48ee-aa83-df5ca1800db5
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 6da5970f-fbcc-4885-a229-c7aa96c72467
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8793
 
 ## 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        | 0.0010 | 1    | 2.2292          |
+| 2.1487        | 0.0097 | 10   | 2.1091          |
+| 1.9949        | 0.0194 | 20   | 1.9761          |
+| 1.9446        | 0.0291 | 30   | 1.9136          |
+| 1.9043        | 0.0388 | 40   | 1.8833          |
+| 1.8676        | 0.0485 | 50   | 1.8793          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335ce224517d6a7919b82f684c1fe44df6ed02591442d821219cca80b5662983
+oid sha256:ee6d0bb04dc47125c4637383d03eb12f0087faf6ff6bb868fe7576517299a4aa
 size 25342042