End of training

README.md

@@ -64,7 +64,7 @@ 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/1af03003d135629c_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 4dee6e01-3061-4ce5-8ac7-b2660fba13f2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4dee6e01-3061-4ce5-8ac7-b2660fba13f2
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 4dee6e01-3061-4ce5-8ac7-b2660fba13f2
 
 This model is a fine-tuned version of [HuggingFaceH4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceH4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## 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        | 0.0039 | 1    | nan             |
+| 10.3785       | 0.0390 | 10   | nan             |
+| 10.3672       | 0.0780 | 20   | nan             |
+| 10.3772       | 0.1170 | 30   | nan             |
+| 10.3873       | 0.1559 | 40   | nan             |
+| 10.4081       | 0.1949 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1649a9f518dacf029763a4602f9d13e44bf83dc57d16ef507bd4542ed9ebff46
+oid sha256:45a3436e10ecf2430676437a5dbc6805a8ff620a1b827ab97e9c2ba19006673e
 size 33666