End of training

README.md

@@ -75,7 +75,7 @@ lora_target_modules:
 lr_scheduler: cosine
 max_memory:
   0: 70GiB
-max_steps: 5
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/bb875996e902a1b4_train_data.json
 model_type: AutoModelForCausalLM
@@ -144,15 +144,16 @@ The following hyperparameters were used during training:
 - 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: 10
-- training_steps: 5
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 0.0           | 0.0159 | 1    | nan             |
-| 0.0           | 0.0318 | 2    | nan             |
-| 0.0           | 0.0636 | 4    | nan             |
+| 0.0           | 0.2066 | 13   | nan             |
+| 0.0           | 0.4131 | 26   | nan             |
+| 0.0           | 0.6197 | 39   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed02991bfb14856da116f62902d9b2b607b6956ef4be3e6652547d461916967
+oid sha256:8cda401164255b2616f72c3e7fd30cf6cdb721c14c93ccb97e5d32785a145e65
 size 37070634