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/eb6e596fa4907cde_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 00ed5451-0c4c-405a-a3ce-b7b87b5a6110
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 00ed5451-0c4c-405a-a3ce-b7b87b5a6110
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 00ed5451-0c4c-405a-a3ce-b7b87b5a6110
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6077
 
 ## 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        | 0.0002 | 1    | 1.6512          |
+| 1.5982        | 0.0016 | 10   | 1.6495          |
+| 1.6642        | 0.0033 | 20   | 1.6372          |
+| 1.6137        | 0.0049 | 30   | 1.6191          |
+| 1.5326        | 0.0065 | 40   | 1.6095          |
+| 1.5964        | 0.0081 | 50   | 1.6077          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f4fbb21a68c58465597595e0a954a4fe6f593335f015a104e2833e7add6943
+oid sha256:1f50e4e71ad940d34d03b241e25f24019291797a155621153b4ee1dcc7ac5708
 size 25342042