| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.666666666666667, | |
| "eval_steps": 500, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 7.484724060219609, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.1681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.829131756518376, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.1712, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 6.664738586442681, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 1.1399, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 3.3584066110083803, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 1.0693, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 3.442370114366976, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 1.0587, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 3.56669601049149, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 1.0467, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 3.7867450428586493, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9659, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 3.335254231811083, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.9521, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 3.0201486501211114, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.9181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 2.1291562708961274, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.883, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 2.2331674865390463, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 0.8161, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.5926856923354156, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.7876, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.2789248216760856, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.7916, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.2902886924531696, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.7473, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.9921992943923053, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.7337, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.2564364639133383, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.7291, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.9308298989088688, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.7087, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.8656622992325634, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.7155, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.8833122782033153, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.7182, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 7.393225273569773, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.6887, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3701068669512917, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.6928, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.9300509606319867, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.5924, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 1.0080266962573095, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.5783, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 1.0171300238506318, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.5365, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 1.0869352839148714, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.5672, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.9352917707943944, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.5471, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.993521936112931, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.5512, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.9930650263586331, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5206, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.974105528692108, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.5612, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.7181078494690534, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.5221, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 1.103522827508161, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.5776, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.8303489757452878, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.5098, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.8903290470299019, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.4652, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.7691679182805314, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.4647, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.8793575084895185, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.3883, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.7939936564361072, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.4612, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.7197516044980385, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.416, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.6671406349191635, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.3956, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.7440093237406595, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.4029, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.7753199974148295, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.4192, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.8295304396639599, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.4103, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.6905026252396183, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.3936, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.6460976497116867, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.36, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.5661215485831413, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.3508, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.6575394619885413, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.3752, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.5600906657273061, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.3458, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.5345328508008275, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.3336, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.5062595557522536, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.3038, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.5400689758849032, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.3211, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.5310247032056505, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.3365, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.518898644519975, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.3369, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.5254824086989422, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.3433, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.5021916764888207, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.3293, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.4669975382305803, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.3245, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.4577103294748289, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.3289, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.3976260825196007, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.2791, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.42070433621682796, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.2922, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.38740869241789666, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.2699, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.39143917552785173, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.3225, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.3655735116880477, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.2777, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.39040760721698864, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.2655, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.3709207628693518, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.2869, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.34592781426824, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.3139, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.36905837602390407, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.2995, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.33021532282471866, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.2728, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.3412788352995484, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.2758, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.38759192979056284, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.2703, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.3156250948411893, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.2773, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.3281474911839613, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.2819, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.3391994826898966, | |
| "learning_rate": 0.0, | |
| "loss": 0.2673, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 8.788556475321549e+16, | |
| "train_loss": 0.5346557378768921, | |
| "train_runtime": 2433.5668, | |
| "train_samples_per_second": 2.876, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 70, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 8.788556475321549e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |