| { | |
| "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": 6.32699446285564, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.0168, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.216389213147966, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.0035, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 5.694821016290401, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.9787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.12063046518324, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.8653, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 4.3165831097992164, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.8841, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.643398206620053, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.8904, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.6535637257333455, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8593, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 3.8645113364268693, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.9134, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 3.236773637488579, | |
| "learning_rate": 1.9950307753654016e-05, | |
| "loss": 0.8542, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 2.290172519078237, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.7494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 3.1175322079012973, | |
| "learning_rate": 1.9801724878485438e-05, | |
| "loss": 1.1513, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.478788148628097, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.6914, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 1.4073302354138626, | |
| "learning_rate": 1.955572805786141e-05, | |
| "loss": 0.7698, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.087801044054887, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.6833, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 1.0150242669966207, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.6941, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.02920290936874, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.7138, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.7938200208795393, | |
| "learning_rate": 1.8782215733702286e-05, | |
| "loss": 0.6876, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.7644360655943776, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.6569, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.7738910441910665, | |
| "learning_rate": 1.826238774315995e-05, | |
| "loss": 0.6804, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.8665884250270166, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.669, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.0006704618779023, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 1.0463, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.7627623192909737, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.6104, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.7070430358484571, | |
| "learning_rate": 1.698236818086073e-05, | |
| "loss": 0.5758, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.6285326680415382, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.5868, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.8521204703237324, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.5713, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.659963008903411, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.5495, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.8404616307697866, | |
| "learning_rate": 1.5425462638657597e-05, | |
| "loss": 0.5446, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.6450431617995342, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5656, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.8109367267270425, | |
| "learning_rate": 1.4562106573531632e-05, | |
| "loss": 0.5698, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.7822006180117975, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.5384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.6909326770002322, | |
| "learning_rate": 1.3653410243663953e-05, | |
| "loss": 0.5533, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 1.0371767584005058, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.8171, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.142857142857143, | |
| "grad_norm": 0.5493737150457074, | |
| "learning_rate": 1.2708404681430054e-05, | |
| "loss": 0.4809, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.6065425678460107, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.4285, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.5977780365463442, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.5016, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.5995676189108186, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.4666, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.5238095238095237, | |
| "grad_norm": 0.5040526924094056, | |
| "learning_rate": 1.0747300935864245e-05, | |
| "loss": 0.4287, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.6264690030331865, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.4742, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.7142857142857144, | |
| "grad_norm": 0.5952037216432571, | |
| "learning_rate": 9.750693082619274e-06, | |
| "loss": 0.4461, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.49400644988972686, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.4567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": 0.5342698652879779, | |
| "learning_rate": 8.756562953525151e-06, | |
| "loss": 0.4571, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.9198473791952313, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.656, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.48339593705836886, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.3975, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.5270723767249225, | |
| "learning_rate": 7.291595318569951e-06, | |
| "loss": 0.3918, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.285714285714286, | |
| "grad_norm": 0.5033564332068363, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.3888, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.4928672320598103, | |
| "learning_rate": 6.34658975633605e-06, | |
| "loss": 0.3874, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.476190476190476, | |
| "grad_norm": 0.5413097166024791, | |
| "learning_rate": 5.887128968693887e-06, | |
| "loss": 0.3953, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.47035578848645737, | |
| "learning_rate": 5.43789342646837e-06, | |
| "loss": 0.3969, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.4462507123762198, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.3541, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.44780944338212697, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.3693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "grad_norm": 0.4412144662214479, | |
| "learning_rate": 4.162563277652104e-06, | |
| "loss": 0.3998, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.4422814183790497, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.3729, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.0476190476190474, | |
| "grad_norm": 0.7076951360385566, | |
| "learning_rate": 3.3831416240314085e-06, | |
| "loss": 0.57, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 0.4236271411002395, | |
| "learning_rate": 3.017631819139273e-06, | |
| "loss": 0.3423, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.238095238095238, | |
| "grad_norm": 0.398124872675547, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.3211, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.40027096396866896, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.3377, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.428571428571429, | |
| "grad_norm": 0.49392287005381574, | |
| "learning_rate": 2.0286749277707783e-06, | |
| "loss": 0.339, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.523809523809524, | |
| "grad_norm": 0.5040093823841447, | |
| "learning_rate": 1.7376122568400533e-06, | |
| "loss": 0.3375, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.619047619047619, | |
| "grad_norm": 0.48433244646529344, | |
| "learning_rate": 1.467091183678444e-06, | |
| "loss": 0.3628, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 0.39192017078456404, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.3256, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.809523809523809, | |
| "grad_norm": 0.39676566849162076, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.3484, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.904761904761905, | |
| "grad_norm": 0.34287489271575816, | |
| "learning_rate": 7.852378812959227e-07, | |
| "loss": 0.3199, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.5902162475062765, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.5283, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.095238095238095, | |
| "grad_norm": 0.4123636905859628, | |
| "learning_rate": 4.4427194213859216e-07, | |
| "loss": 0.3219, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.190476190476191, | |
| "grad_norm": 0.3867909512226697, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.3216, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.285714285714286, | |
| "grad_norm": 0.37928691730528397, | |
| "learning_rate": 1.9827512151456175e-07, | |
| "loss": 0.3271, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.380952380952381, | |
| "grad_norm": 0.3542995140094366, | |
| "learning_rate": 1.1169173774871478e-07, | |
| "loss": 0.3377, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.476190476190476, | |
| "grad_norm": 0.39163320395055434, | |
| "learning_rate": 4.9692246345985905e-08, | |
| "loss": 0.333, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 0.3583502876426602, | |
| "learning_rate": 1.2430787810776556e-08, | |
| "loss": 0.3153, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.3362212776164937, | |
| "learning_rate": 0.0, | |
| "loss": 0.3277, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "step": 70, | |
| "total_flos": 1.1879483303159398e+17, | |
| "train_loss": 0.5572643731321607, | |
| "train_runtime": 2364.533, | |
| "train_samples_per_second": 2.96, | |
| "train_steps_per_second": 0.03 | |
| } | |
| ], | |
| "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": 1.1879483303159398e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |