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/a923ad5a1ae9f0bb_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 5f55735d-60e4-4e05-8268-a0245ae002a1
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5f55735d-60e4-4e05-8268-a0245ae002a1
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # a5b02956-df61-54b8-61e9-7edbe1c5824e
 
 This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.0823
 
 ## 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    | 11.0861         |
+| 44.3467       | 0.0020 | 10   | 11.0855         |
+| 44.348        | 0.0039 | 20   | 11.0842         |
+| 44.3405       | 0.0059 | 30   | 11.0831         |
+| 44.3347       | 0.0078 | 40   | 11.0824         |
+| 44.3286       | 0.0098 | 50   | 11.0823         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7dbd9c6b50aa0414b80871ef570f6ec808caf791e879bd3d695d343905a84d
+oid sha256:eacff63984e5c9298059918fb66c97aaaa6d792cd5343953f00174ac34c48ffb
 size 37022