| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028668354914233838, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003822447321897845, | |
| "grad_norm": 6.0184736251831055, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.6425, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003822447321897845, | |
| "eval_loss": 5.886753082275391, | |
| "eval_runtime": 235.5914, | |
| "eval_samples_per_second": 9.355, | |
| "eval_steps_per_second": 4.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000764489464379569, | |
| "grad_norm": 6.729464530944824, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.965, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011467341965693536, | |
| "grad_norm": 6.846334457397461, | |
| "learning_rate": 0.0001, | |
| "loss": 4.804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001528978928759138, | |
| "grad_norm": 5.922602653503418, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 4.5205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019112236609489226, | |
| "grad_norm": 4.700122833251953, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 4.2375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022934683931387072, | |
| "grad_norm": 5.692227363586426, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.5447, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0026757131253284916, | |
| "grad_norm": 6.327576637268066, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 4.0891, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003057957857518276, | |
| "grad_norm": 7.014576435089111, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 4.6651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034402025897080604, | |
| "grad_norm": 5.033721923828125, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.0995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0038224473218978453, | |
| "grad_norm": 4.756032943725586, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 4.1288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00420469205408763, | |
| "grad_norm": 4.503414154052734, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.9138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0045869367862774145, | |
| "grad_norm": 5.417407035827637, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0049691815184671985, | |
| "grad_norm": 4.673385143280029, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.6087, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005351426250656983, | |
| "grad_norm": 4.72328519821167, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 4.0141, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005733670982846767, | |
| "grad_norm": 4.933603286743164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006115915715036552, | |
| "grad_norm": 4.5453972816467285, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 3.3622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006498160447226337, | |
| "grad_norm": 4.865222930908203, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.2046, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006880405179416121, | |
| "grad_norm": 5.340005397796631, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.3491, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007262649911605906, | |
| "grad_norm": 4.902261257171631, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.2672, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0076448946437956905, | |
| "grad_norm": 5.233785152435303, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 2.9632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008027139375985475, | |
| "grad_norm": 4.948408603668213, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2824, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00840938410817526, | |
| "grad_norm": 5.471080303192139, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 2.6134, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008791628840365044, | |
| "grad_norm": 5.066695213317871, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.939, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009173873572554829, | |
| "grad_norm": 5.192546844482422, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.0767, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009556118304744612, | |
| "grad_norm": 5.16768741607666, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 2.9899, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009556118304744612, | |
| "eval_loss": 2.9074714183807373, | |
| "eval_runtime": 237.9901, | |
| "eval_samples_per_second": 9.261, | |
| "eval_steps_per_second": 4.63, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009938363036934397, | |
| "grad_norm": 5.4715962409973145, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 2.5455, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010320607769124182, | |
| "grad_norm": 5.549165725708008, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5844, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010702852501313967, | |
| "grad_norm": 5.676646709442139, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 2.7422, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011085097233503751, | |
| "grad_norm": 5.423862934112549, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 2.4021, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011467341965693535, | |
| "grad_norm": 6.854278087615967, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01184958669788332, | |
| "grad_norm": 5.748988628387451, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.633, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012231831430073104, | |
| "grad_norm": 5.561115741729736, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 2.2951, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012614076162262889, | |
| "grad_norm": 5.736785411834717, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.2345, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012996320894452674, | |
| "grad_norm": 5.680880546569824, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 2.535, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013378565626642459, | |
| "grad_norm": 5.533990859985352, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.159, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013760810358832242, | |
| "grad_norm": 6.057872295379639, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.066, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.014143055091022027, | |
| "grad_norm": 6.172090530395508, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 2.301, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014525299823211811, | |
| "grad_norm": 4.52834415435791, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.3066, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014907544555401596, | |
| "grad_norm": 5.488335132598877, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1805, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015289789287591381, | |
| "grad_norm": 5.258327960968018, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.64, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015672034019781164, | |
| "grad_norm": 6.46604585647583, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 2.6909, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01605427875197095, | |
| "grad_norm": 6.989088535308838, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.8893, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016436523484160734, | |
| "grad_norm": 4.715562343597412, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.3926, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01681876821635052, | |
| "grad_norm": 5.3317975997924805, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.7183, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017201012948540303, | |
| "grad_norm": 4.577286720275879, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01758325768073009, | |
| "grad_norm": 6.528746128082275, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 2.253, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017965502412919873, | |
| "grad_norm": 5.994633674621582, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 2.0534, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.018347747145109658, | |
| "grad_norm": 8.008041381835938, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4081, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01872999187729944, | |
| "grad_norm": 9.006482124328613, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 2.7403, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.019112236609489224, | |
| "grad_norm": 17.78826904296875, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 4.5138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019112236609489224, | |
| "eval_loss": 2.8716228008270264, | |
| "eval_runtime": 238.2191, | |
| "eval_samples_per_second": 9.252, | |
| "eval_steps_per_second": 4.626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01949448134167901, | |
| "grad_norm": 9.267752647399902, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.2077, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.019876726073868794, | |
| "grad_norm": 9.39410400390625, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 4.1575, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02025897080605858, | |
| "grad_norm": 8.945734977722168, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 3.9224, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.020641215538248363, | |
| "grad_norm": 8.452441215515137, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.3653, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02102346027043815, | |
| "grad_norm": 7.56348180770874, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 3.7901, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.021405705002627933, | |
| "grad_norm": 7.109958648681641, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 3.9603, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.021787949734817718, | |
| "grad_norm": 7.252974987030029, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.7393, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.022170194467007503, | |
| "grad_norm": 6.574551105499268, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 3.5858, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.022552439199197288, | |
| "grad_norm": 5.8216447830200195, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 3.341, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.02293468393138707, | |
| "grad_norm": 5.938989162445068, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.22, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.023316928663576854, | |
| "grad_norm": 5.049765110015869, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 3.3303, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.02369917339576664, | |
| "grad_norm": 4.824350357055664, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 3.2963, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.024081418127956424, | |
| "grad_norm": 5.315403461456299, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.9856, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02446366286014621, | |
| "grad_norm": 4.886056900024414, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 2.9163, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024845907592335993, | |
| "grad_norm": 5.032073497772217, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 3.2227, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.025228152324525778, | |
| "grad_norm": 4.646665573120117, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.1442, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.025610397056715563, | |
| "grad_norm": 4.919647216796875, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 3.1255, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.025992641788905348, | |
| "grad_norm": 5.229823112487793, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 2.7633, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.026374886521095132, | |
| "grad_norm": 4.874609470367432, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.9428, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.026757131253284917, | |
| "grad_norm": 4.912359714508057, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 2.9206, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0271393759854747, | |
| "grad_norm": 4.882635593414307, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 2.7132, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.027521620717664484, | |
| "grad_norm": 4.96625280380249, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.6065, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02790386544985427, | |
| "grad_norm": 5.217054843902588, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 2.7019, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.028286110182044053, | |
| "grad_norm": 5.2616705894470215, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 2.5789, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.028668354914233838, | |
| "grad_norm": 5.830911159515381, | |
| "learning_rate": 0.0, | |
| "loss": 3.0903, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.028668354914233838, | |
| "eval_loss": 2.6363327503204346, | |
| "eval_runtime": 238.1673, | |
| "eval_samples_per_second": 9.254, | |
| "eval_steps_per_second": 4.627, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.98024458780672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |