{ "best_metric": 0.348395973443985, "best_model_checkpoint": "plantuml-code-generation/checkpoint-300", "epoch": 6.70391061452514, "eval_steps": 50, "global_step": 300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.44692737430167595, "grad_norm": 6.86284875869751, "learning_rate": 8e-05, "loss": 6.1395, "step": 20 }, { "epoch": 0.8938547486033519, "grad_norm": 0.13778135180473328, "learning_rate": 0.00016, "loss": 1.2405, "step": 40 }, { "epoch": 1.1173184357541899, "eval_loss": 0.6436046361923218, "eval_runtime": 57.1725, "eval_samples_per_second": 3.148, "eval_steps_per_second": 0.402, "step": 50 }, { "epoch": 1.3407821229050279, "grad_norm": 0.07968226820230484, "learning_rate": 0.000192, "loss": 0.6601, "step": 60 }, { "epoch": 1.7877094972067038, "grad_norm": 0.0890984982252121, "learning_rate": 0.00017600000000000002, "loss": 0.5855, "step": 80 }, { "epoch": 2.2346368715083798, "grad_norm": 0.09667715430259705, "learning_rate": 0.00016, "loss": 0.5319, "step": 100 }, { "epoch": 2.2346368715083798, "eval_loss": 0.48206308484077454, "eval_runtime": 57.1888, "eval_samples_per_second": 3.147, "eval_steps_per_second": 0.402, "step": 100 }, { "epoch": 2.6815642458100557, "grad_norm": 0.12260276824235916, "learning_rate": 0.000144, "loss": 0.4477, "step": 120 }, { "epoch": 3.1284916201117317, "grad_norm": 0.12728622555732727, "learning_rate": 0.00012800000000000002, "loss": 0.4241, "step": 140 }, { "epoch": 3.35195530726257, "eval_loss": 0.4002044200897217, "eval_runtime": 57.5487, "eval_samples_per_second": 3.128, "eval_steps_per_second": 0.4, "step": 150 }, { "epoch": 3.5754189944134076, "grad_norm": 0.14667275547981262, "learning_rate": 0.00011200000000000001, "loss": 0.381, "step": 160 }, { "epoch": 4.022346368715084, "grad_norm": 0.14442357420921326, "learning_rate": 9.6e-05, "loss": 0.3836, "step": 180 }, { "epoch": 4.4692737430167595, "grad_norm": 0.16686952114105225, "learning_rate": 8e-05, "loss": 0.3524, "step": 200 }, { "epoch": 4.4692737430167595, "eval_loss": 0.36753496527671814, "eval_runtime": 57.537, "eval_samples_per_second": 3.128, "eval_steps_per_second": 0.4, "step": 200 }, { "epoch": 4.916201117318436, "grad_norm": 0.1686471551656723, "learning_rate": 6.400000000000001e-05, "loss": 0.3484, "step": 220 }, { "epoch": 5.363128491620111, "grad_norm": 0.18261033296585083, "learning_rate": 4.8e-05, "loss": 0.3547, "step": 240 }, { "epoch": 5.58659217877095, "eval_loss": 0.35252371430397034, "eval_runtime": 57.4948, "eval_samples_per_second": 3.131, "eval_steps_per_second": 0.4, "step": 250 }, { "epoch": 5.810055865921788, "grad_norm": 0.1722261905670166, "learning_rate": 3.2000000000000005e-05, "loss": 0.3282, "step": 260 }, { "epoch": 6.256983240223463, "grad_norm": 0.1778961718082428, "learning_rate": 1.6000000000000003e-05, "loss": 0.3403, "step": 280 }, { "epoch": 6.70391061452514, "grad_norm": 0.18417717516422272, "learning_rate": 0.0, "loss": 0.3202, "step": 300 }, { "epoch": 6.70391061452514, "eval_loss": 0.348395973443985, "eval_runtime": 57.5812, "eval_samples_per_second": 3.126, "eval_steps_per_second": 0.399, "step": 300 } ], "logging_steps": 20, "max_steps": 300, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.9650799214592e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }