End of training

README.md

@@ -18,6 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
+auto_find_batch_size: true
 base_model: katuni4ka/tiny-random-dbrx
 bf16: auto
 chat_template: llama3
@@ -65,7 +66,7 @@ lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 99
-micro_batch_size: 16
+micro_batch_size: 8
 mlflow_experiment_name: /tmp/f1fb178455e95e80_train_data.json
 model_type: AutoModelForCausalLM
 num_epochs: 1
@@ -122,8 +123,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
@@ -134,8 +135,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.0031 | 1    | 11.5            |
-| 11.5          | 0.1553 | 50   | 11.5            |
+| No log        | 0.0016 | 1    | 11.5            |
+| 11.5          | 0.0778 | 50   | 11.5            |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb695301b465ad407f443dcc4d464d6d6d49197785c634716886725f9f1efae
+oid sha256:7e3a66310ef2cc438504a3240fb8d6729c1e6b8af05c667a166b8fd1ebb2dd6f
 size 9170