Best model so far - eval_loss: 7.0156 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.5755 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.5563 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.5860 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.5939 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.7216 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 6.9000 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.9229 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.9351 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.3263 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 6.9147 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.2714 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 6.9045 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.9153 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 6.9216 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.2796 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 7.2365 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.2840 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.5118 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 7.9472 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 7.8779 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 1.0983 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1304 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.1819 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.2814 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 1.3151 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 1.3238 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 0.0015 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.0022 -------------------------------------------------------- (Trained with Unsloth)

Best model so far - eval_loss: 0.0022 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 0.0153 -------------------------------------------------------- (Trained with Unsloth)

Initial model state ------------------------------------------------------------------------ (Trained with Unsloth)

Best model so far - eval_loss: 0.0018 --------------------------------------------------------

Best model so far - eval_loss: 0.0019 --------------------------------------------------------

Best model so far - eval_loss: 0.0022 --------------------------------------------------------

Best model so far - eval_loss: 0.0025 --------------------------------------------------------

Best model so far - eval_loss: 0.0040 --------------------------------------------------------

Best model so far - eval_loss: 0.0041 --------------------------------------------------------

Best model so far - eval_loss: 0.0097 --------------------------------------------------------