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/7c6b0eb56390e951_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 47fc7627-5614-43ba-b420-fda2e1cb2bd7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 47fc7627-5614-43ba-b420-fda2e1cb2bd7
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 843b8ca3-ce61-7aad-6b83-e59e1e68eb52
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1367
 
 ## 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    | 0.6168          |
+| 0.4494        | 0.0020 | 10   | 0.3781          |
+| 0.1783        | 0.0041 | 20   | 0.1594          |
+| 0.1393        | 0.0061 | 30   | 0.1411          |
+| 0.1276        | 0.0082 | 40   | 0.1373          |
+| 0.1291        | 0.0102 | 50   | 0.1367          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1951036758a6426b80e3b700c08a2fe146c162c0659f47ceac32ca1a6d09ad5e
+oid sha256:a1b470ca376f04cd2a548e3961911894b49deb2a9ed64d70ae17c82ec1ea433b
 size 84047370