| { | |
| "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": 6.158669250370364, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.9754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.391638516515913, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.0266, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 5.64086870790543, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.959, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.3855976467730797, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.9016, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 4.2245345608911204, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.8735, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.907842576206414, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.9284, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 5.246325605567945, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9073, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 3.6065994368039833, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.8202, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 3.125264301143519, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.7722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 2.274286528707033, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.7806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 3.3909742973715415, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 1.1001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.7744278657443242, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.772, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.5317108772544004, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.6417, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.2973566464149455, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.6787, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.02691660912025, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.7013, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.3900240258969938, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.7016, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 1.0187831395730613, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.6427, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.8629496101351887, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.6914, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 1.1135569631731865, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.671, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.7736472845784272, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.6423, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.405510448766131, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.9805, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.9626596063159919, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.5992, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.7369509039814478, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.5613, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.7729522323358596, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.5565, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.6665618012602051, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.5565, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.679543206302224, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.5222, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.6611814009914206, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.5442, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.5500102766857, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5099, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.7142776979004015, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.5415, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.6649566492113868, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.5344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.6769095338434882, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.5304, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 1.0391867881789734, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.8056, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.6439846583921891, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.4466, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.603427001038118, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.4376, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.6337882243812638, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.4222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.5736362723718568, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.433, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.7121419317251309, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.399, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.7071697404895783, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.4481, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.5151518832467246, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.4142, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.5594119625081236, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.4362, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.5673468077595174, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.4175, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.8240308492016023, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.5878, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.5383103337244857, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.3523, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.565449013145426, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.3733, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.5333946833407351, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.3477, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.5677636358062432, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.3453, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.6301362586061847, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.3638, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.5381657669400263, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.3419, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.4671370164849908, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.3363, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.47709792166388815, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.3241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.4823715285282104, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.3436, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.5619662796911007, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.3535, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.7797851609803315, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.4575, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.5333729632923118, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.3077, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.4936097776424722, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.2877, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.5206722787251671, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.3299, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.4647584782937841, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.2679, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.5578903218240157, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.3166, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.517116303705823, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.3198, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.4764096683319275, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.2882, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.37763064502765165, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.2581, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.4392904606425341, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.3232, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.6690278662641393, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.4054, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.47222565245233133, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.3008, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.4366477149934331, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.2852, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.3784676296607786, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.2766, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.43817969131926715, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.2692, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.4097741330497312, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.2853, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.3898017574181228, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.2827, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.4332839702959375, | |
| "learning_rate": 0.0, | |
| "loss": 0.2963, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 9.88978976087081e+16, | |
| "train_loss": 0.5273114276783807, | |
| "train_runtime": 2129.7353, | |
| "train_samples_per_second": 3.287, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "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": 9.88978976087081e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |