| { | |
| "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": 6.462877231182179, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.0227, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.157030485311083, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.9996, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 5.560394573428609, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.9765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.397298490014312, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.8893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 4.4587766170696295, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.9081, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.945600594395545, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.8802, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 5.2489634654029285, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8789, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 4.035400321274088, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.8812, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 4.054365777007484, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.8704, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 2.827061078648691, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.8102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 3.4368871988709717, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 1.1674, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.8752433742869237, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.7546, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.6257737156617267, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.6845, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.6455260839629926, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.7132, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.1761381742255934, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.758, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.1984447093625692, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.672, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 1.0025337669373362, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.6714, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.9539204142501372, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.648, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.8306192874836518, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.7103, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.9293579447433404, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.6309, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.0266475956915337, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.9181, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.9052616680337231, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.5679, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.7327593555194516, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.5525, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.8233026429312902, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.5529, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.6924032936943956, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.5327, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 2.3633877830830423, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.549, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.792019308145649, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.5434, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.670255740500361, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5333, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.7458807652618739, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.5221, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.6337853117251886, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.5244, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.6385709415797348, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.5162, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 1.0325780708325558, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.7286, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.6523583590801426, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.4108, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.590301402916656, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.4329, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.6269515773605866, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.4124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.6647435227157746, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.4214, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.6135621233599271, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.4383, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.7506969620221331, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.4211, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.5717003034388145, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.4011, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.6409124119892052, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.4122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.5659323791218944, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.3929, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.8340483954956339, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.5756, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.5632526227663072, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.3713, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.5662682655059569, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.3579, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.5326280134874097, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.3312, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.49347751879994023, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.318, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.5741724875463765, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.3199, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.5518141860891244, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.3085, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.5384231866910034, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.3254, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.47150974956344976, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.3107, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.5271287567439377, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.2942, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.4543352847658043, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.3078, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.7644145556932647, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.4628, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.5311987466707925, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.2658, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.524590143408793, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.2621, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.4578783582898461, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.2846, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.4536112139094287, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.2746, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.4932806327495905, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.2617, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.5640079642060352, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.3054, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.5069324524711732, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.2455, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.4915262642478055, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.2764, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.49261816421616733, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.3167, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.6791413251253293, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.3487, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.385825995047788, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.251, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.39349412523453475, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.2677, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.4124669304515733, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.2562, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.4299456700090585, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.2554, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.41669332564677813, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.2421, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.41174075488168127, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.2444, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.4409529195811459, | |
| "learning_rate": 0.0, | |
| "loss": 0.2602, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 8.56302861502382e+16, | |
| "train_loss": 0.5173346500311579, | |
| "train_runtime": 1782.2733, | |
| "train_samples_per_second": 3.928, | |
| "train_steps_per_second": 0.039 | |
| } | |
| ], | |
| "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": 8.56302861502382e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |