{ "best_metric": null, "best_model_checkpoint": null, "epoch": 14.693877551020408, "eval_steps": 500, "global_step": 360, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.40816326530612246, "grad_norm": 9.136496543884277, "learning_rate": 1.9444444444444445e-05, "loss": 3.1546, "step": 10 }, { "epoch": 0.8163265306122449, "grad_norm": 9.660746574401855, "learning_rate": 1.888888888888889e-05, "loss": 2.8102, "step": 20 }, { "epoch": 1.2244897959183674, "grad_norm": 9.723041534423828, "learning_rate": 1.8333333333333333e-05, "loss": 2.525, "step": 30 }, { "epoch": 1.6326530612244898, "grad_norm": 9.724725723266602, "learning_rate": 1.7777777777777777e-05, "loss": 2.3084, "step": 40 }, { "epoch": 2.0408163265306123, "grad_norm": 9.782754898071289, "learning_rate": 1.7222222222222224e-05, "loss": 2.0958, "step": 50 }, { "epoch": 2.4489795918367347, "grad_norm": 9.011795043945312, "learning_rate": 1.6666666666666667e-05, "loss": 1.9128, "step": 60 }, { "epoch": 2.857142857142857, "grad_norm": 9.87028694152832, "learning_rate": 1.6111111111111115e-05, "loss": 1.7905, "step": 70 }, { "epoch": 3.2653061224489797, "grad_norm": 10.717073440551758, "learning_rate": 1.555555555555556e-05, "loss": 1.6279, "step": 80 }, { "epoch": 3.673469387755102, "grad_norm": 9.600900650024414, "learning_rate": 1.5000000000000002e-05, "loss": 1.5752, "step": 90 }, { "epoch": 4.081632653061225, "grad_norm": 9.698976516723633, "learning_rate": 1.4444444444444446e-05, "loss": 1.4379, "step": 100 }, { "epoch": 4.489795918367347, "grad_norm": 7.813742160797119, "learning_rate": 1.388888888888889e-05, "loss": 1.3803, "step": 110 }, { "epoch": 4.8979591836734695, "grad_norm": 8.631564140319824, "learning_rate": 1.3333333333333333e-05, "loss": 1.3613, "step": 120 }, { "epoch": 5.3061224489795915, "grad_norm": 7.81006383895874, "learning_rate": 1.2777777777777777e-05, "loss": 1.2634, "step": 130 }, { "epoch": 5.714285714285714, "grad_norm": 8.972601890563965, "learning_rate": 1.2222222222222224e-05, "loss": 1.2105, "step": 140 }, { "epoch": 6.122448979591836, "grad_norm": 8.98891830444336, "learning_rate": 1.1666666666666668e-05, "loss": 1.1679, "step": 150 }, { "epoch": 6.530612244897959, "grad_norm": 8.04240894317627, "learning_rate": 1.1111111111111113e-05, "loss": 1.1352, "step": 160 }, { "epoch": 6.938775510204081, "grad_norm": 7.237417221069336, "learning_rate": 1.0555555555555557e-05, "loss": 1.1537, "step": 170 }, { "epoch": 7.346938775510204, "grad_norm": 7.013981342315674, "learning_rate": 1e-05, "loss": 1.0737, "step": 180 }, { "epoch": 7.755102040816326, "grad_norm": 7.11979341506958, "learning_rate": 9.444444444444445e-06, "loss": 1.0782, "step": 190 }, { "epoch": 8.16326530612245, "grad_norm": 6.833500862121582, "learning_rate": 8.888888888888888e-06, "loss": 1.0569, "step": 200 }, { "epoch": 8.571428571428571, "grad_norm": 7.029465675354004, "learning_rate": 8.333333333333334e-06, "loss": 1.0092, "step": 210 }, { "epoch": 8.979591836734693, "grad_norm": 7.06866455078125, "learning_rate": 7.77777777777778e-06, "loss": 1.0287, "step": 220 }, { "epoch": 9.387755102040817, "grad_norm": 6.73593282699585, "learning_rate": 7.222222222222223e-06, "loss": 1.0327, "step": 230 }, { "epoch": 9.795918367346939, "grad_norm": 7.02034854888916, "learning_rate": 6.666666666666667e-06, "loss": 0.9739, "step": 240 }, { "epoch": 10.204081632653061, "grad_norm": 5.793264865875244, "learning_rate": 6.111111111111112e-06, "loss": 0.952, "step": 250 }, { "epoch": 10.612244897959183, "grad_norm": 6.729996681213379, "learning_rate": 5.555555555555557e-06, "loss": 0.9955, "step": 260 }, { "epoch": 11.020408163265307, "grad_norm": 5.858097553253174, "learning_rate": 5e-06, "loss": 0.9239, "step": 270 }, { "epoch": 11.428571428571429, "grad_norm": 7.36622428894043, "learning_rate": 4.444444444444444e-06, "loss": 0.9975, "step": 280 }, { "epoch": 11.83673469387755, "grad_norm": 5.627753734588623, "learning_rate": 3.88888888888889e-06, "loss": 0.8992, "step": 290 }, { "epoch": 12.244897959183673, "grad_norm": 5.971806049346924, "learning_rate": 3.3333333333333333e-06, "loss": 0.9506, "step": 300 }, { "epoch": 12.653061224489797, "grad_norm": 6.324193954467773, "learning_rate": 2.7777777777777783e-06, "loss": 0.9165, "step": 310 }, { "epoch": 13.061224489795919, "grad_norm": 5.6594648361206055, "learning_rate": 2.222222222222222e-06, "loss": 0.921, "step": 320 }, { "epoch": 13.46938775510204, "grad_norm": 5.637096405029297, "learning_rate": 1.6666666666666667e-06, "loss": 0.9104, "step": 330 }, { "epoch": 13.877551020408163, "grad_norm": 7.2482075691223145, "learning_rate": 1.111111111111111e-06, "loss": 0.9573, "step": 340 }, { "epoch": 14.285714285714286, "grad_norm": 7.663059234619141, "learning_rate": 5.555555555555555e-07, "loss": 0.9104, "step": 350 }, { "epoch": 14.693877551020408, "grad_norm": 6.165991306304932, "learning_rate": 0.0, "loss": 0.8955, "step": 360 } ], "logging_steps": 10, "max_steps": 360, "num_input_tokens_seen": 0, "num_train_epochs": 15, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 181443311981568.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }