| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999310202110782, | |
| "eval_steps": 500, | |
| "global_step": 453, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022073532454990687, | |
| "grad_norm": 1.114385199189024, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 0.8555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044147064909981375, | |
| "grad_norm": 0.4068262714558307, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.7997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06622059736497206, | |
| "grad_norm": 0.38632787233483873, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 0.7758, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08829412981996275, | |
| "grad_norm": 0.33047790751954587, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.7616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11036766227495344, | |
| "grad_norm": 1.0326147215252546, | |
| "learning_rate": 4.9988084660498037e-05, | |
| "loss": 0.7609, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13244119472994412, | |
| "grad_norm": 0.36413735150639703, | |
| "learning_rate": 4.985416749673074e-05, | |
| "loss": 0.7677, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1545147271849348, | |
| "grad_norm": 0.23884890145764054, | |
| "learning_rate": 4.957223915853709e-05, | |
| "loss": 0.7558, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1765882596399255, | |
| "grad_norm": 0.35792840187365693, | |
| "learning_rate": 4.9143978581429445e-05, | |
| "loss": 0.7492, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1986617920949162, | |
| "grad_norm": 0.24556724333359267, | |
| "learning_rate": 4.857193613652711e-05, | |
| "loss": 0.7497, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22073532454990688, | |
| "grad_norm": 0.2087162197069783, | |
| "learning_rate": 4.78595184426236e-05, | |
| "loss": 0.7433, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24280885700489757, | |
| "grad_norm": 0.30705087020634647, | |
| "learning_rate": 4.7010968079140294e-05, | |
| "loss": 0.744, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26488238945988823, | |
| "grad_norm": 0.2021404929324958, | |
| "learning_rate": 4.6031338320779534e-05, | |
| "loss": 0.7378, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.28695592191487895, | |
| "grad_norm": 0.3679260523738371, | |
| "learning_rate": 4.492646304433711e-05, | |
| "loss": 0.7388, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3090294543698696, | |
| "grad_norm": 0.2575945484350903, | |
| "learning_rate": 4.3702921986884574e-05, | |
| "loss": 0.7301, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.33110298682486033, | |
| "grad_norm": 0.1987923782298564, | |
| "learning_rate": 4.236800156221536e-05, | |
| "loss": 0.7407, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.353176519279851, | |
| "grad_norm": 0.22541496226647023, | |
| "learning_rate": 4.092965146890002e-05, | |
| "loss": 0.7319, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3752500517348417, | |
| "grad_norm": 0.1903443234063274, | |
| "learning_rate": 3.9396437348357684e-05, | |
| "loss": 0.7292, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3973235841898324, | |
| "grad_norm": 0.2786630443541303, | |
| "learning_rate": 3.777748977487366e-05, | |
| "loss": 0.7488, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.41939711664482304, | |
| "grad_norm": 0.22941720588230605, | |
| "learning_rate": 3.608244988133713e-05, | |
| "loss": 0.7305, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.44147064909981376, | |
| "grad_norm": 0.2244920841625261, | |
| "learning_rate": 3.432141194450772e-05, | |
| "loss": 0.7329, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4635441815548044, | |
| "grad_norm": 0.20271098423902761, | |
| "learning_rate": 3.2504863271726286e-05, | |
| "loss": 0.729, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.48561771400979514, | |
| "grad_norm": 0.21017591515648715, | |
| "learning_rate": 3.064362174705578e-05, | |
| "loss": 0.7392, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5076912464647858, | |
| "grad_norm": 0.16688378969283219, | |
| "learning_rate": 2.8748771408776466e-05, | |
| "loss": 0.7323, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5297647789197765, | |
| "grad_norm": 0.18531081231895546, | |
| "learning_rate": 2.683159644188339e-05, | |
| "loss": 0.7391, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5518383113747672, | |
| "grad_norm": 0.1949891552768074, | |
| "learning_rate": 2.4903513978673077e-05, | |
| "loss": 0.7304, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5739118438297579, | |
| "grad_norm": 0.1847538114841563, | |
| "learning_rate": 2.2976006107604482e-05, | |
| "loss": 0.7248, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5959853762847486, | |
| "grad_norm": 0.17808591988598846, | |
| "learning_rate": 2.1060551495333818e-05, | |
| "loss": 0.7361, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6180589087397392, | |
| "grad_norm": 0.15634167603442348, | |
| "learning_rate": 1.9168557029126963e-05, | |
| "loss": 0.7205, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6401324411947299, | |
| "grad_norm": 0.16800926021112392, | |
| "learning_rate": 1.7311289886731408e-05, | |
| "loss": 0.7215, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6622059736497207, | |
| "grad_norm": 0.15374716011431305, | |
| "learning_rate": 1.549981043824425e-05, | |
| "loss": 0.7204, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6842795061047113, | |
| "grad_norm": 0.1358494068080939, | |
| "learning_rate": 1.3744906379558165e-05, | |
| "loss": 0.7217, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.706353038559702, | |
| "grad_norm": 0.1598338460219363, | |
| "learning_rate": 1.2057028489632682e-05, | |
| "loss": 0.7288, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7284265710146927, | |
| "grad_norm": 0.1552517836620765, | |
| "learning_rate": 1.0446228394168356e-05, | |
| "loss": 0.7128, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7505001034696834, | |
| "grad_norm": 0.1363267921768715, | |
| "learning_rate": 8.922098706312548e-06, | |
| "loss": 0.7212, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7725736359246741, | |
| "grad_norm": 0.1417947472753852, | |
| "learning_rate": 7.493715900870027e-06, | |
| "loss": 0.7109, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7946471683796648, | |
| "grad_norm": 0.13261081741759453, | |
| "learning_rate": 6.169586262213081e-06, | |
| "loss": 0.7206, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8167207008346554, | |
| "grad_norm": 0.13329678652766908, | |
| "learning_rate": 4.957595227781395e-06, | |
| "loss": 0.7166, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8387942332896461, | |
| "grad_norm": 0.13079371602746745, | |
| "learning_rate": 3.864960428840375e-06, | |
| "loss": 0.7095, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8608677657446369, | |
| "grad_norm": 0.12980162903604736, | |
| "learning_rate": 2.8981887081491576e-06, | |
| "loss": 0.7088, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8829412981996275, | |
| "grad_norm": 0.12204737322722421, | |
| "learning_rate": 2.0630373705058407e-06, | |
| "loss": 0.7189, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9050148306546182, | |
| "grad_norm": 0.12227603852992606, | |
| "learning_rate": 1.3644798969302403e-06, | |
| "loss": 0.7215, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9270883631096088, | |
| "grad_norm": 0.12433131124525597, | |
| "learning_rate": 8.066763266625282e-07, | |
| "loss": 0.7155, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9491618955645996, | |
| "grad_norm": 0.12167710585090329, | |
| "learning_rate": 3.929484833584546e-07, | |
| "loss": 0.7076, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9712354280195903, | |
| "grad_norm": 0.12190898417393506, | |
| "learning_rate": 1.2576019301373532e-07, | |
| "loss": 0.7176, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.993308960474581, | |
| "grad_norm": 0.1232187443009331, | |
| "learning_rate": 6.702611423550775e-09, | |
| "loss": 0.7082, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9999310202110782, | |
| "step": 453, | |
| "total_flos": 3799534094254080.0, | |
| "train_loss": 0.7359120230011592, | |
| "train_runtime": 173906.7289, | |
| "train_samples_per_second": 1.334, | |
| "train_steps_per_second": 0.003 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 453, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 3799534094254080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |