| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012743622215319427, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002548724443063885, | |
| "grad_norm": 10.957205772399902, | |
| "learning_rate": 5e-05, | |
| "loss": 23.1908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002548724443063885, | |
| "eval_loss": 1.2135640382766724, | |
| "eval_runtime": 4.933, | |
| "eval_samples_per_second": 10.136, | |
| "eval_steps_per_second": 2.635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000509744888612777, | |
| "grad_norm": 5.463685989379883, | |
| "learning_rate": 0.0001, | |
| "loss": 22.6914, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007646173329191656, | |
| "grad_norm": 19.589599609375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 30.1611, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001019489777225554, | |
| "grad_norm": 7.9456787109375, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 25.5741, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012743622215319428, | |
| "grad_norm": 11.475204467773438, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 27.5682, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015292346658383313, | |
| "grad_norm": 9.603759765625, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 25.9038, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017841071101447198, | |
| "grad_norm": 15.269070625305176, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 30.7353, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002038979554451108, | |
| "grad_norm": 11.179081916809082, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 29.3103, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002293851998757497, | |
| "grad_norm": 16.421573638916016, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 32.3899, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025487244430638855, | |
| "grad_norm": 18.604475021362305, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 34.6395, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002803596887370274, | |
| "grad_norm": 21.579675674438477, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 37.2472, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0030584693316766626, | |
| "grad_norm": 13.824583053588867, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 37.4721, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003313341775983051, | |
| "grad_norm": 17.34259033203125, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 31.2821, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0035682142202894396, | |
| "grad_norm": 14.09797191619873, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 20.9543, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003823086664595828, | |
| "grad_norm": 16.875381469726562, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 22.5457, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004077959108902216, | |
| "grad_norm": 15.8306303024292, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 24.5114, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004332831553208605, | |
| "grad_norm": 14.515591621398926, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 24.4274, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004587703997514994, | |
| "grad_norm": 11.320648193359375, | |
| "learning_rate": 7.75e-05, | |
| "loss": 23.6507, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004842576441821382, | |
| "grad_norm": 9.57024097442627, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 23.9403, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005097448886127771, | |
| "grad_norm": 8.522046089172363, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 25.5635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005352321330434159, | |
| "grad_norm": 8.201630592346191, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 27.0895, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005607193774740548, | |
| "grad_norm": 12.267687797546387, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 27.9509, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005862066219046936, | |
| "grad_norm": 12.899337768554688, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 28.2821, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006116938663353325, | |
| "grad_norm": 12.832313537597656, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 30.7911, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006371811107659713, | |
| "grad_norm": 25.457059860229492, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 40.7172, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006371811107659713, | |
| "eval_loss": 0.846438467502594, | |
| "eval_runtime": 4.9576, | |
| "eval_samples_per_second": 10.086, | |
| "eval_steps_per_second": 2.622, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006626683551966102, | |
| "grad_norm": 4.532904624938965, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 18.5507, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006881555996272491, | |
| "grad_norm": 4.218832969665527, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 21.4172, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007136428440578879, | |
| "grad_norm": 9.199362754821777, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 22.3767, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0073913008848852674, | |
| "grad_norm": 5.325526237487793, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 24.2828, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007646173329191656, | |
| "grad_norm": 5.052194595336914, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 21.9941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007901045773498044, | |
| "grad_norm": 6.375118255615234, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 23.9578, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008155918217804432, | |
| "grad_norm": 7.436459064483643, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 23.0201, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008410790662110822, | |
| "grad_norm": 7.55717658996582, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 26.8142, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00866566310641721, | |
| "grad_norm": 10.21662712097168, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 26.6104, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008920535550723599, | |
| "grad_norm": 9.883365631103516, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 26.0736, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009175407995029987, | |
| "grad_norm": 14.174981117248535, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 28.5612, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009430280439336376, | |
| "grad_norm": 29.440217971801758, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 35.2239, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009685152883642764, | |
| "grad_norm": 26.214704513549805, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 26.3995, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009940025327949152, | |
| "grad_norm": 5.275035381317139, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 20.0292, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010194897772255542, | |
| "grad_norm": 3.81276798248291, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 20.0261, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01044977021656193, | |
| "grad_norm": 7.4508376121521, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 20.7993, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010704642660868319, | |
| "grad_norm": 4.377939701080322, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 21.0901, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010959515105174707, | |
| "grad_norm": 5.861658573150635, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 21.6036, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011214387549481095, | |
| "grad_norm": 4.197175025939941, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 22.2189, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011469259993787484, | |
| "grad_norm": 4.8456010818481445, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 23.1757, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011724132438093872, | |
| "grad_norm": 21.775585174560547, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 24.6419, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.011979004882400262, | |
| "grad_norm": 11.26821231842041, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 25.9023, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01223387732670665, | |
| "grad_norm": 10.412407875061035, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 27.6609, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012488749771013039, | |
| "grad_norm": 13.727615356445312, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 26.2059, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012743622215319427, | |
| "grad_norm": 21.477025985717773, | |
| "learning_rate": 1e-05, | |
| "loss": 34.0621, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012743622215319427, | |
| "eval_loss": 0.8061414957046509, | |
| "eval_runtime": 4.9334, | |
| "eval_samples_per_second": 10.135, | |
| "eval_steps_per_second": 2.635, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 3.0139627627505254e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |