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/6863c794fb898ea9_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 6866240e-d493-4beb-8991-d9a5610c05d7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 6866240e-d493-4beb-8991-d9a5610c05d7
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # a23ff189-be10-458a-8d32-a5194a020543
 
 This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 8.7016
 
 ## 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        | 0.0019 | 1    | 8.9716          |
+| 36.8309       | 0.0187 | 10   | 8.9723          |
+| 34.8422       | 0.0374 | 20   | 8.8112          |
+| 34.6401       | 0.0561 | 30   | 8.7239          |
+| 35.5796       | 0.0748 | 40   | 8.7061          |
+| 37.1808       | 0.0935 | 50   | 8.7016          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd31c72b727fbedba96a3c46c87b189b0b932ebf684b56313e1d47473e16783b
+oid sha256:5f457c1b0373bbe6b768f5fdb0b9bee2a92d08affbfa746c66cc8caf0332fce8
 size 410814