| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 63, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 2.636066198348999, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.5447, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 1.7816333770751953, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.1323, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 2.2745041847229004, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2092, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 2.6683919429779053, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.5569, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 2.3222100734710693, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.4135, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 2.067908525466919, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 2.5608789920806885, | |
| "learning_rate": 1.9984815164333163e-05, | |
| "loss": 1.4595, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.3394458293914795, | |
| "learning_rate": 1.9939306773179498e-05, | |
| "loss": 1.0971, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 2.624566078186035, | |
| "learning_rate": 1.9863613034027224e-05, | |
| "loss": 1.3249, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 3.019270420074463, | |
| "learning_rate": 1.9757963826274357e-05, | |
| "loss": 1.1663, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5238095238095238, | |
| "grad_norm": 4.040117263793945, | |
| "learning_rate": 1.9622680003092503e-05, | |
| "loss": 1.3519, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 5.076770782470703, | |
| "learning_rate": 1.9458172417006347e-05, | |
| "loss": 1.212, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6190476190476191, | |
| "grad_norm": 3.281177282333374, | |
| "learning_rate": 1.9264940672148018e-05, | |
| "loss": 0.8725, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 3.5001425743103027, | |
| "learning_rate": 1.9043571606975776e-05, | |
| "loss": 0.6642, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 2.4256069660186768, | |
| "learning_rate": 1.879473751206489e-05, | |
| "loss": 0.5313, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 2.3582112789154053, | |
| "learning_rate": 1.851919408838327e-05, | |
| "loss": 0.73, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8095238095238095, | |
| "grad_norm": 1.449530005455017, | |
| "learning_rate": 1.821777815225245e-05, | |
| "loss": 0.3238, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 2.057817220687866, | |
| "learning_rate": 1.789140509396394e-05, | |
| "loss": 0.3367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9047619047619048, | |
| "grad_norm": 1.7016539573669434, | |
| "learning_rate": 1.7541066097768965e-05, | |
| "loss": 0.3914, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.2818858623504639, | |
| "learning_rate": 1.7167825131684516e-05, | |
| "loss": 0.1852, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9452447891235352, | |
| "learning_rate": 1.6772815716257414e-05, | |
| "loss": 0.1722, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 0.5685144662857056, | |
| "learning_rate": 1.6357237482099682e-05, | |
| "loss": 0.0953, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0952380952380953, | |
| "grad_norm": 0.6435515880584717, | |
| "learning_rate": 1.5922352526649803e-05, | |
| "loss": 0.1832, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.049676537513733, | |
| "learning_rate": 1.5469481581224274e-05, | |
| "loss": 0.402, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1904761904761905, | |
| "grad_norm": 0.9065538048744202, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.2622, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 0.5284762978553772, | |
| "learning_rate": 1.4515333583108896e-05, | |
| "loss": 0.1086, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.7903798222541809, | |
| "learning_rate": 1.4016954246529697e-05, | |
| "loss": 0.0996, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.2656748294830322, | |
| "learning_rate": 1.3506375551927546e-05, | |
| "loss": 0.0154, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 1.171624779701233, | |
| "learning_rate": 1.2985148110016947e-05, | |
| "loss": 0.2659, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.31690454483032227, | |
| "learning_rate": 1.2454854871407993e-05, | |
| "loss": 0.0673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4761904761904763, | |
| "grad_norm": 0.7295234799385071, | |
| "learning_rate": 1.1917106319237386e-05, | |
| "loss": 0.2074, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.6296242475509644, | |
| "learning_rate": 1.1373535578184083e-05, | |
| "loss": 0.1208, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 1.0464074611663818, | |
| "learning_rate": 1.0825793454723325e-05, | |
| "loss": 0.2525, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.4286152422428131, | |
| "learning_rate": 1.0275543423681622e-05, | |
| "loss": 0.1035, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.5248931646347046, | |
| "learning_rate": 9.724456576318383e-06, | |
| "loss": 0.1614, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.40034690499305725, | |
| "learning_rate": 9.174206545276678e-06, | |
| "loss": 0.1218, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7619047619047619, | |
| "grad_norm": 0.4369080662727356, | |
| "learning_rate": 8.626464421815919e-06, | |
| "loss": 0.06, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 1.110698938369751, | |
| "learning_rate": 8.082893680762619e-06, | |
| "loss": 0.3501, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.314057320356369, | |
| "learning_rate": 7.545145128592009e-06, | |
| "loss": 0.0499, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.9931963086128235, | |
| "learning_rate": 7.014851889983058e-06, | |
| "loss": 0.1744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9523809523809523, | |
| "grad_norm": 0.31384727358818054, | |
| "learning_rate": 6.4936244480724575e-06, | |
| "loss": 0.0713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.4129275977611542, | |
| "learning_rate": 5.983045753470308e-06, | |
| "loss": 0.0776, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0476190476190474, | |
| "grad_norm": 0.31003817915916443, | |
| "learning_rate": 5.484666416891109e-06, | |
| "loss": 0.043, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.5723528265953064, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0901, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.6738455295562744, | |
| "learning_rate": 4.530518418775734e-06, | |
| "loss": 0.1227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.1904761904761907, | |
| "grad_norm": 0.5331130027770996, | |
| "learning_rate": 4.077647473350201e-06, | |
| "loss": 0.1491, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.238095238095238, | |
| "grad_norm": 0.4636727571487427, | |
| "learning_rate": 3.6427625179003223e-06, | |
| "loss": 0.0874, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.5442101359367371, | |
| "learning_rate": 3.2271842837425917e-06, | |
| "loss": 0.1945, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 0.3890051543712616, | |
| "learning_rate": 2.8321748683154893e-06, | |
| "loss": 0.1032, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.4027661085128784, | |
| "learning_rate": 2.4589339022310386e-06, | |
| "loss": 0.1239, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 0.5832112431526184, | |
| "learning_rate": 2.1085949060360654e-06, | |
| "loss": 0.1892, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.29090118408203125, | |
| "learning_rate": 1.7822218477475496e-06, | |
| "loss": 0.0538, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.5238095238095237, | |
| "grad_norm": 1.1339997053146362, | |
| "learning_rate": 1.4808059116167306e-06, | |
| "loss": 0.256, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.41949254274368286, | |
| "learning_rate": 1.2052624879351105e-06, | |
| "loss": 0.0908, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.619047619047619, | |
| "grad_norm": 0.7024145126342773, | |
| "learning_rate": 9.564283930242258e-07, | |
| "loss": 0.1081, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.236419215798378, | |
| "learning_rate": 7.350593278519824e-07, | |
| "loss": 0.0255, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 0.49600574374198914, | |
| "learning_rate": 5.418275829936537e-07, | |
| "loss": 0.1057, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.2218826860189438, | |
| "learning_rate": 3.773199969074959e-07, | |
| "loss": 0.0306, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.8095238095238093, | |
| "grad_norm": 0.793448269367218, | |
| "learning_rate": 2.420361737256438e-07, | |
| "loss": 0.0991, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.2536832094192505, | |
| "learning_rate": 1.3638696597277678e-07, | |
| "loss": 0.0382, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.9047619047619047, | |
| "grad_norm": 0.38577455282211304, | |
| "learning_rate": 6.069322682050516e-08, | |
| "loss": 0.0753, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 0.2848428785800934, | |
| "learning_rate": 1.518483566683826e-08, | |
| "loss": 0.0502, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.2466929852962494, | |
| "learning_rate": 0.0, | |
| "loss": 0.032, | |
| "step": 63 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 63, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2094121699246080.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |