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/9c38a59c659abe71_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: f4e4807c-e5f8-4ee5-9d8c-dae32453864f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f4e4807c-e5f8-4ee5-9d8c-dae32453864f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 9f3e3617-2846-4ac9-8f28-7acdb9f8d78f
 
 This model is a fine-tuned version of [katuni4ka/tiny-random-falcon-40b](https://huggingface.co/katuni4ka/tiny-random-falcon-40b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.0992
 
 ## 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        | 0.0001 | 1    | 11.1131         |
+| 44.4543       | 0.0012 | 10   | 11.1115         |
+| 44.4189       | 0.0024 | 20   | 11.1069         |
+| 44.4096       | 0.0036 | 30   | 11.1024         |
+| 44.403        | 0.0048 | 40   | 11.0997         |
+| 44.406        | 0.0060 | 50   | 11.0992         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7dc6be2b4729f36611395c4424bb2a6e9c59c7d7a72a1e05df7b8d0e0c8740
+oid sha256:3a4dcb1db3f2278c5cf2ca89b17ce0c5324cba4e2624f1bf81bf1fbbc2532095
 size 129182