| { | |
| "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": 6.518212470378846, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.0484, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.587528529000099, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.0477, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 5.9824742944345095, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 1.0239, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.8247619928281877, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.9707, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 4.148158334165783, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.9516, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.381779840589696, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.9588, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.140751972726175, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9207, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 2.954091299952174, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.8828, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 2.351514314592787, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.8362, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.5794144544087108, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.7998, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 2.0629065112208305, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 1.2229, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.2860786592265527, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.7605, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.1910602453723949, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.7905, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.0953254404761612, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.695, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.1578797823598195, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.7683, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.1760841836308957, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.762, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.8714825773690721, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.6573, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.94873606383788, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.7097, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.8951886609154117, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.6851, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.7867579521377509, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.7499, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.1475048381969282, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 1.0128, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.7348961313820965, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.6568, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.7131868615442395, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.6609, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.760537957157173, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.6579, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.5972522498908271, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.6283, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.7786495477065015, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.6227, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.725947883704514, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.6369, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.704663124546637, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.623, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.7884749156155324, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.6153, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.6890730354353558, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.6066, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.605161555100844, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.6193, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.962860319895067, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.8645, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.5738476612999261, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.6039, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.5840064742243171, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.5792, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.48734724202059726, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.5745, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.5042921073151893, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.5501, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.5116385124189319, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.5759, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.49856827886397076, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.5844, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.41385053944230626, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.5163, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.502976399008024, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.5796, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.471416846154755, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.5052, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.7552055603191463, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.8603, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.490918321678198, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.5393, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.5965615889176096, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.5203, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.4643882480068538, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.5165, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.45058368032549867, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.5066, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.4816892118134155, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.5163, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.44971728833802255, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.5095, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.48469532379433633, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.5093, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.3704729631438316, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.5121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.3570173560386269, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.5097, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.44002402557950926, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.5074, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.6807163852906846, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.7554, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.3074241890120183, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.4943, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.3753271169190582, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.5083, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.3775287344690129, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.4687, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.3444811821839712, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.4545, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.3376918642935278, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.5258, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.32848729600847976, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.493, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.34075492376610994, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.4899, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.3020199394879285, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.4378, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.3167555828910423, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.4995, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.47472248835572706, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.7396, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.2685001460523142, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.4855, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.2688660442454094, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.477, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.26691359090490074, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.4782, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.28163683547084395, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.4759, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.2833035558570076, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.4613, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.25566377284374026, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.4822, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.28218666179330326, | |
| "learning_rate": 0.0, | |
| "loss": 0.4768, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 1.90120829386752e+17, | |
| "train_loss": 0.6532361681972231, | |
| "train_runtime": 3137.1757, | |
| "train_samples_per_second": 2.231, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "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": 1.90120829386752e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |