End of training

README.md

@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.3855
-- eval_model_preparation_time: 0.0013
-- eval_runtime: 14.0825
-- eval_samples_per_second: 743.05
-- eval_steps_per_second: 5.823
-- epoch: 1.1292
-- step: 9521
+- eval_loss: 3.9086
+- eval_model_preparation_time: 0.0016
+- eval_runtime: 16.8971
+- eval_samples_per_second: 619.276
+- eval_steps_per_second: 5.563
+- epoch: 13.5067
+- step: 130151
 
 ## Model description
 
@@ -42,8 +42,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 112
+- eval_batch_size: 112
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0b4f47c6c19b7fcd15025ed45df083d19cafe45cd25f48b8908a63a3a92ad9
+oid sha256:cc9d06f25b7839d69de2d44fc4a6cfdb22d4028b359825727477246bb02836e4
 size 826798720

runs/Jan16_11-25-23_81d9b8b5d266/events.out.tfevents.1737026742.81d9b8b5d266.25767.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b93b6f9de348c9e9de91668dd7539eaca0edf4f2b8418a940126c78bbe2a2a6
-size 65564
+oid sha256:83833ff100378b6807f73d36f032cc5d04186389790200c22ab7ee812b0a0483
+size 65907