| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 774, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03875968992248062, | |
| "grad_norm": 2.577054727951972, | |
| "learning_rate": 2e-06, | |
| "loss": 0.721, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07751937984496124, | |
| "grad_norm": 1.3292498101090573, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6438, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 2.3414148705752926, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6248, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 2.621497754252154, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6155, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1937984496124031, | |
| "grad_norm": 1.642709929025015, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6022, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 1.4108572822591154, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6008, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2713178294573643, | |
| "grad_norm": 1.8320230338483412, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5995, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 2.0509677067609906, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5919, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 1.8615028380190877, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5883, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3875968992248062, | |
| "grad_norm": 1.651732467548723, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5867, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4263565891472868, | |
| "grad_norm": 1.827483286285098, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5824, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 1.878984672982078, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5768, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5038759689922481, | |
| "grad_norm": 1.461881748693503, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5791, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5426356589147286, | |
| "grad_norm": 1.7965397328352164, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5769, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 1.9228942975753127, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5808, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 1.1676070598043125, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5704, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6589147286821705, | |
| "grad_norm": 1.1754765506774811, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5689, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 1.7812488410180551, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5668, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7364341085271318, | |
| "grad_norm": 1.808692259046032, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5753, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 1.8584614057755389, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5652, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 1.599864515399134, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5683, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8527131782945736, | |
| "grad_norm": 1.6516869387309938, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5673, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8914728682170543, | |
| "grad_norm": 1.6848137903140608, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5643, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 1.3032607046739686, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5649, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9689922480620154, | |
| "grad_norm": 1.5431955138670315, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5597, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0077519379844961, | |
| "grad_norm": 2.0310291210286238, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5571, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "grad_norm": 1.2551497648955234, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5299, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0852713178294573, | |
| "grad_norm": 1.1678057917636586, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5317, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.124031007751938, | |
| "grad_norm": 1.125227296422933, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5275, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "grad_norm": 1.3900860537725233, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5236, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2015503875968991, | |
| "grad_norm": 1.2021576698979493, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5306, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2403100775193798, | |
| "grad_norm": 1.2053080767276194, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5277, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.2790697674418605, | |
| "grad_norm": 1.3991030309565773, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5274, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3178294573643412, | |
| "grad_norm": 1.1826629752006035, | |
| "learning_rate": 2e-06, | |
| "loss": 0.531, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3565891472868217, | |
| "grad_norm": 1.1287968703954268, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5275, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "grad_norm": 1.5127256802296236, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5317, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.4341085271317828, | |
| "grad_norm": 1.5013875357775832, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5297, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.4728682170542635, | |
| "grad_norm": 1.7614327167944768, | |
| "learning_rate": 2e-06, | |
| "loss": 0.526, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.5116279069767442, | |
| "grad_norm": 1.4214027958077065, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5293, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.550387596899225, | |
| "grad_norm": 1.6564120069131323, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5255, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5891472868217056, | |
| "grad_norm": 1.378206427304318, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5211, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "grad_norm": 1.988629014217936, | |
| "learning_rate": 2e-06, | |
| "loss": 0.526, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.9503056920319735, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5288, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.7054263565891472, | |
| "grad_norm": 1.732782542682626, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5241, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.744186046511628, | |
| "grad_norm": 1.528224415622805, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5272, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7829457364341086, | |
| "grad_norm": 1.1793820983967487, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5226, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8217054263565893, | |
| "grad_norm": 1.1809068975224493, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5242, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 1.379981502891672, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5273, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.8992248062015504, | |
| "grad_norm": 1.8940459651264965, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5236, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.937984496124031, | |
| "grad_norm": 1.898050329402726, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5263, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9767441860465116, | |
| "grad_norm": 1.6806097447928925, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5231, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.0155038759689923, | |
| "grad_norm": 1.7706824956520133, | |
| "learning_rate": 2e-06, | |
| "loss": 0.5092, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.054263565891473, | |
| "grad_norm": 1.1944302472248438, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4867, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 1.3491176032576682, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4842, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.1317829457364343, | |
| "grad_norm": 1.182447255831288, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4843, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.1705426356589146, | |
| "grad_norm": 1.0865626136425315, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4878, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.2093023255813953, | |
| "grad_norm": 1.1893887821883726, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4852, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.248062015503876, | |
| "grad_norm": 1.197021602818726, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4858, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.2868217054263567, | |
| "grad_norm": 1.0736236283669167, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4893, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "grad_norm": 1.017760123624255, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4858, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.3643410852713176, | |
| "grad_norm": 1.1866183343445358, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4893, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.4031007751937983, | |
| "grad_norm": 1.0875734211472181, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4893, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.441860465116279, | |
| "grad_norm": 1.4175668384873126, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4879, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.4806201550387597, | |
| "grad_norm": 1.5445789270591548, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4905, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.5193798449612403, | |
| "grad_norm": 1.1527990919509379, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4861, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.558139534883721, | |
| "grad_norm": 1.0983296348010934, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4893, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.5968992248062017, | |
| "grad_norm": 1.7393177878547021, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4915, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.6356589147286824, | |
| "grad_norm": 1.6766013258821928, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4847, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.6744186046511627, | |
| "grad_norm": 1.5674228297707393, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4876, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.7131782945736433, | |
| "grad_norm": 1.5303183442776453, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4876, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.751937984496124, | |
| "grad_norm": 1.830851000547026, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4839, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.7906976744186047, | |
| "grad_norm": 1.7047867407889794, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4898, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.8294573643410854, | |
| "grad_norm": 1.5112038359871813, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4899, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.8682170542635657, | |
| "grad_norm": 1.4351025379161033, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4892, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.9069767441860463, | |
| "grad_norm": 1.222684031513469, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4864, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.945736434108527, | |
| "grad_norm": 1.3407496538423456, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4881, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.9844961240310077, | |
| "grad_norm": 1.5499167243320089, | |
| "learning_rate": 2e-06, | |
| "loss": 0.488, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 774, | |
| "total_flos": 2591282618695680.0, | |
| "train_loss": 0.5347004343372906, | |
| "train_runtime": 11473.9369, | |
| "train_samples_per_second": 69.018, | |
| "train_steps_per_second": 0.067 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 774, | |
| "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": 2591282618695680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |