End of training

README.md

@@ -65,7 +65,7 @@ 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/ae189b11c0f4805d_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: ce3c9590-cca9-41d9-9475-e91355958041
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ce3c9590-cca9-41d9-9475-e91355958041
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # d3183849-ab94-4ef1-96ec-c86d4cf5fa61
 
 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: 11.0663
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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    | 11.1168         |
+| 44.4713       | 0.0012 | 10   | 11.1092         |
+| 44.3678       | 0.0025 | 20   | 11.0913         |
+| 44.3088       | 0.0037 | 30   | 11.0758         |
+| 44.2717       | 0.0049 | 40   | 11.0677         |
+| 44.2775       | 0.0062 | 50   | 11.0663         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b4e9fb1b8a416e29685e4ec57cf43a74a766a5a8f80e9525190067f339bf3a
+oid sha256:42221c176feacd831dbc6ee3f96ad01d3e9574945007781d8a74ca745ff53fc5
 size 129182