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/0c86e0af3fecf3d8_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 0e02b55c-c41d-42e2-b123-ff9d66a5b791
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0e02b55c-c41d-42e2-b123-ff9d66a5b791
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 3e20f975-260a-afd6-84fd-a4d0b23e7565
 
 This model is a fine-tuned version of [OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5](https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8459
 
 ## 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        | 0.0004 | 1    | 2.0534          |
+| 7.909         | 0.0036 | 10   | 1.6814          |
+| 4.6893        | 0.0072 | 20   | 1.0644          |
+| 3.6895        | 0.0108 | 30   | 0.9001          |
+| 3.4593        | 0.0144 | 40   | 0.8535          |
+| 3.4048        | 0.0180 | 50   | 0.8459          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0479613084849e48888514fad0743c83795cd679f3a7aaf9b32a50f67b34977e
+oid sha256:3dc082468609ed4b69d4646e3232099abcd523259f859a8caf4ddf1c3e0a8996
 size 94477642