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/1cdad3506d86664d_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 0c862fee-2042-414b-98c3-2b6c8e57613b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0c862fee-2042-414b-98c3-2b6c8e57613b
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 7ad1eb43-e5d7-6c2a-43de-a49c7a94061e
 
 This model is a fine-tuned version of [scb10x/llama-3-typhoon-v1.5-8b-instruct](https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1845
 
 ## 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        | 0.0010 | 1    | 3.3628          |
+| 3.0893        | 0.0100 | 10   | 2.8220          |
+| 2.3623        | 0.0200 | 20   | 2.3811          |
+| 2.5382        | 0.0300 | 30   | 2.2507          |
+| 2.2113        | 0.0400 | 40   | 2.1949          |
+| 2.1962        | 0.0500 | 50   | 2.1845          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd6790eb3ecb4e88a392306b6bc0afbad704319acf304b5ba131b28abee56a3
+oid sha256:b0b87e9987a836961d48c7328658f3c646ba8c15b76809e707bf0427fc660972
 size 84047370